Messages in this thread | | | Date | Thu, 1 Apr 2010 15:48:47 -0700 | From | Jesse Barnes <> | Subject | Re: [Regression, post-rc2] Commit a5ee4eb7541 breaks OpenGL on RS780 (was: Re: Linux 2.6.34-rc3) |
| |
On Thu, 1 Apr 2010 09:29:23 -0700 (PDT) Linus Torvalds <torvalds@linux-foundation.org> wrote:
> > > On Thu, 1 Apr 2010, Rafael J. Wysocki wrote: > > > > OK, I've verified that partial revert (below) is sufficient. > > Hmm. Through the DRM merge I just did, this area actually conflicted, and > the resolved version is now > > if ((rdev->family >= CHIP_RV380) && > (!(rdev->flags & RADEON_IS_IGP))) { > > which presumably also fixes your issue? > > [ Side note: somebody in the DRM tree seems to be way too used to LISP, > and thinks that adding parenthesis always improves the code ;-] > > However, I do suspect that we should probably revert the quirk regardless > as being useless (ie it probably was related to those IGP chips that > apparently don't do MSI anyway). > > So the patch that reverts the quirk by Clemens (to replace it with > disabling MSI entirely when the AMD NB doesn't accept them) seems to be a > good idea regardless, since it's apparently not just about gfx. Jesse?
Yeah, that sounds fine. I can include it in my next pull req or you can just pick it up directly.
-- Jesse Barnes, Intel Open Source Technology Center
| |