On Sun, 27 May 2012 18:26:05 -0700, Linus Torvalds torvalds@linux-foundation.org wrote:
i915_error_state contents attached. I haven't done the bejeweled thing in a while, but it used to work fine, so I'm pretty sure this is new. There seems to have been a fair amount of ringbuffer and fencing work by Chris since 3.4, so..
Any other information I can give you guys?
No, the i915_error_state had everything I needed to see. It is the old ddx bug that was hardcoding a maximum relocation address that never corresponded with an actual hw limit. As soon we try to use memory above that value, the GPU decides not to listen to us any more.
Fixed in xf86-video-intel 2.14.901 -Chris