On Tue, Apr 07, 2015 at 11:12:09AM +0100, Chris Wilson wrote:
> On Tue, Apr 07, 2015 at 11:07:07AM +0200, Daniel Vetter wrote:
> > On Tue, Apr 07, 2015 at 09:36:37AM +0100, Chris Wilson wrote:
> > > On Tue, Apr 07, 2015 at 10:10:25AM +0200, Daniel Vetter wrote:
> > > > On Thu, Apr 02, 2015 at 12:15:13AM +0100, Chris Wilson wrote:
> > > > > On Wed, Apr 01, 2015 at 07:40:59PM -0300, Paulo Zanoni wrote:
> > > > > > +static void draw_rect_mmap_wc(int fd, struct buf_data *buf, struct rect *rect,
> > > > > > + uint32_t color)
> > > > > > +{
> > > > > > + uint32_t *ptr;
> > > > > > + uint32_t tiling, swizzle;
> > > > > > +
> > > > > > + gem_get_tiling(fd, buf->handle, &tiling, &swizzle);
> > > > > > +
> > > > > > + /* We didn't implement suport for the older tiling methods yet. */
> > > > > > + if (tiling != I915_TILING_NONE)
> > > > > > + igt_require(intel_gen(intel_get_drm_devid(fd)) >= 5);
> > > > >
> > > > > But you now do! You need something like:
> > > >
> > > > The problem is that the kernel hides bit17 swizzling. I chatted with Paulo
> > > > on irc about this and we decided just ignore them all is the simplest
> > > > approach.
> > >
> > > Urm, that was the whole point of GET_TILING v2. That small function is
> > > all you need to determine when bit17 is in effect and then you get to
> > > reuse all the direct CPU methods (as they are also used by userspace)
> > > for earlier gen.
> >
> > Oh right completely forgot that we've added this. But imo can be added on
> > top once we need it (it's not just gen2 but also some gen3 which need
> > different tile dimensions).
>
> Tile size is 2048 for gen2 only right. Tile width is the same for all
> gen3 for tiling X (and gen2), but tiling Y width depends on subgen.
> Right?
>
> Just need to check because I have code that depends on this...
Oh right thought about Y tiling which changes on gen3. X tiling matches
your description afaik - I consider gem_tiled_pread the authoritative
source for this stuff.
-Daniel
--
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
