On Tue, Jan 02, 2018 at 04:43:15PM +, Vladimir Murzin wrote:
> On 29/12/17 08:18, Christoph Hellwig wrote:
> > If we got back an allocation that wasn't inside the support coherent mask,
> > retry the allocation using GFP_DMA.
> >
> > Based on the x86 code.
> >
> > Signed-off-by: Christoph Hel
On Tue, Jan 02, 2018 at 11:36:00AM +0100, Geert Uytterhoeven wrote:
> Hi Christoph,
>
> On Fri, Dec 29, 2017 at 9:18 AM, Christoph Hellwig wrote:
> > CONFIG_ALPHA_JENSEN has failed to compile since commit aca05038
> > ("alpha/dma: use common noop dma ops"), so mark it as broken.
>
> unknown revi
On Fri, Dec 29, 2017 at 03:12:25PM +0100, Geert Uytterhoeven wrote:
> > +check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
> > + const char *caller)
> > +{
> > + if (unlikely(dev && !dma_capable(dev, dma_addr, size))) {
> > + if (*dev->dma_mask >= DM
On Tue, Jan 02, 2018 at 08:45:30PM +1100, Michael Ellerman wrote:
> Christoph Hellwig writes:
>
> > We want to use the dma_direct_ namespace for a generic implementation,
> > so rename powerpc to the second best choice: dma_nommu_.
>
> I'm not a fan of "nommu". Some of the users of direct ops *a
On Wed, Jan 03, 2018 at 07:19:46PM +1100, Julian Calaby wrote:
> If this is indeed a linear mapping, can we just remove this and
> replace it with the new "generic" mapping being introduced by this
> patchset?
That is the long-term plan. But as the powerpc one includes support
for non-coherent DM
On Fri, Dec 29, 2017 at 09:11:56PM +1100, Julian Calaby wrote:
> Hi Christoph,
>
> On Fri, Dec 29, 2017 at 7:18 PM, Christoph Hellwig wrote:
> > This frees the dma_direct_* namespace for a generic implementation.
>
> Don't you mean "dma_nommu" not "dma_microblaze" in the subject line?
Yes, than
