On Wed, Aug 05, 2015 at 05:10:17PM -0300, Tiago Vignatti wrote:
> On 08/05/2015 04:08 AM, Daniel Vetter wrote:
> >On Tue, Aug 04, 2015 at 06:30:25PM -0300, Tiago Vignatti wrote:
> >Nah they don't have to be equal since the problem isn't that nothing goes
> >out to memory where the display can see i
On 08/05/2015 04:08 AM, Daniel Vetter wrote:
> On Tue, Aug 04, 2015 at 06:30:25PM -0300, Tiago Vignatti wrote:
> Nah they don't have to be equal since the problem isn't that nothing goes
> out to memory where the display can see it, but usually only parts of it.
> I.e. you need to change your test
On Tue, Aug 04, 2015 at 06:30:25PM -0300, Tiago Vignatti wrote:
> On 07/31/2015 06:02 PM, Chris Wilson wrote:
> >
> >The first problem is that llc does not guarrantee that the buffer is
> >cache coherent with all aspects of the GPU. For scanout and similar
> >writes need to be WC.
> >
> >if (obj->h
On 07/31/2015 06:02 PM, Chris Wilson wrote:
>
> The first problem is that llc does not guarrantee that the buffer is
> cache coherent with all aspects of the GPU. For scanout and similar
> writes need to be WC.
>
> if (obj->has_framebuffer_references) would at least catch where the fb
> is made bef
On Fri, Jul 31, 2015 at 05:42:23PM -0300, Tiago Vignatti wrote:
> For now we're opting out devices that don't have the LLC CPU cache (mostly
> "Atom" devices). Alternatively, we could build up a path to mmap them through
> GTT WC (and ignore the fact that will be dead-slow for reading). Or, an even
