On Thu, Sep 1, 2011 at 10:16 AM, Jesse Barnes <jbarnes@xxxxxxxxxxxxxxxx> wrote: > Jon, can you take a look at this? Looks like even the "safe" option > causes problems... so either there's a difference in the way the > payload is programmed even in the safe case, or just read/writing that > reg on radeon causes trouble. > > https://bugzilla.kernel.org/show_bug.cgi?id=42162 The issue appears to be with setting MRRS to 0. The Radeon HW doesn't seem to like it, and I'm guessing other devices won't either. Instead of reverting the patch as a whole, I can rip out the MRRS setting code (which I believe is the cause of all of the problems being seen). Thanks, Jon > Thanks, > -- > Jesse Barnes, Intel Open Source Technology Center > -- To unsubscribe from this list: send the line "unsubscribe linux-pci" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
