Messages in this thread | | | From | "Rafael J. Wysocki" <> | Subject | Re: [Regression, post-rc2] Commit a5ee4eb7541 breaks OpenGL on RS780 (was: Re: Linux 2.6.34-rc3) | Date | Fri, 2 Apr 2010 01:23:55 +0200 |
| |
On Friday 02 April 2010, Jesse Barnes wrote: > 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.
Not exactly that one, please, it's missing a quirk for the affected system.
I've just sent a corrected version, here: https://patchwork.kernel.org/patch/90275/
Rafael
| |