On Mon, Feb 10, 2014 at 04:29:45PM +0200, Ville Syrjälä wrote: > On Mon, Feb 10, 2014 at 02:14:54PM +0000, One Thousand Gnomes wrote: > > > > Does this mean it should also handle horizontal mirroring in > > > > hardware (180° rotate, and scan lines backwards combined) ? > > > > > > Our hardware doesn't support mirroring (h or v). Well, unless you > > > count h+v mirroring since that's 180 degree rotation :) > > > > > > Anyways IIRC the old video overlay (present on gen2-4) was the only plane > > > to ever support mirroring on Intel hardware. With all other planes we're > > > limited to 0 and 180 degree rotation > > > > It seems to do vertical mirroring providing your output buffer is > > allocated and aligned on page boundaries as the GTT can then be used to > > map the scan lines in any order you like ? > > Oh, right. That would be possible, but that sounds like something that > needs to be done on the gem side rather than the kms side since it > impacts other things besides scanout memory access. Well either that > or we'd potentially need to map the same object multiple times into > the ggtt. Until someone demonstrates a clear benefit and use-case for that I'll vote "pls just blit it with the render engine". The common use-case for rotation is tablets/phones and there we can't do it in many cases anyway. -Daniel -- Daniel Vetter Software Engineer, Intel Corporation +41 (0) 79 365 57 48 - http://blog.ffwll.ch _______________________________________________ dri-devel mailing list dri-devel@xxxxxxxxxxxxxxxxxxxxx http://lists.freedesktop.org/mailman/listinfo/dri-devel
