On Wed, Apr 24, 2013 at 11:06:12AM +0100, Chris Wilson wrote: > On Tue, Apr 23, 2013 at 11:15:40PM -0700, Ben Widawsky wrote: > > Going forward, every context will have its own address space. So rip off > > the band aid now. If contexts fail, don't do ppgtt, and vice versa. > > > > Similarly to the last patch, this is somewhat wasteful of PPGTT address > > space with contexts, since we're not actually utilizing the new PPGTT. > > What strategy do we have for isolating bugs between ctx and ppggt? I'd > like to be able disable each of them independently and together. > -Chris None. Up through the end of this series we have the ability to turn off: PPGTT or Contexts & PPGTT. Given our history, I think that probably concerns you more than PPGTT. I don't know how to make you feel better.AFAIK, Mesa plans to become dependent on contexts anyway, so having a way of backing out of that, even for debug, seems to be of limited use to me. > > -- > Chris Wilson, Intel Open Source Technology Centre -- Ben Widawsky, Intel Open Source Technology Center
