Hello All, SNB GPU (i7-2620M) still hangs frequently with kernel 3.0-rc4 raising "drm:i915_hangcheck_ring_idle *ERROR* Hangcheck timer elapsed... gen6 bsd ring idle". This happens when multiple applications (mplayer decoding vaapi stream and some openGL game) running at the same time. With either one running there is no stalling. Changing /sys/module/i915/parameters/i915_enable_rc6 to 0 does *NOT* change the situation. However setting /sys/module/i915/parameters/semaphores to 1 kills the stalling but also kills the x-server every couple of minutes or causes the system to freeze when xf86-video-intel is compiled with --enable-sna. Could someone please confirm the issue?
Created attachment 48238 [details] xorg.log
Created attachment 48239 [details] dmesg
Created attachment 48240 [details] deep hwinfo
Created attachment 48241 [details] [review] Apply HWSTAM workaround for BSD ring as well Random patch of the day.
(In reply to comment #4) > Created an attachment (id=48241) [details] > Apply HWSTAM workaround for BSD ring as well > > Random patch of the day. Chris, looks good so far. The patch prevents my system to stall even under heavy CPU and GPU load. Good work! If there are no objections I'll close this bug. Thanks and regards, nic
A patch referencing this bug report has been merged in Linux v3.0-rc5: commit ec6a890dfed7dd245beba5e5bcdfcffbd934c284 Author: Chris Wilson <chris@chris-wilson.co.uk> Date: Tue Jun 21 18:37:59 2011 +0100 drm/i915: Apply HWSTAM workaround for BSD ring on SandyBridge
Use of freedesktop.org services, including Bugzilla, is subject to our Code of Conduct. How we collect and use information is described in our Privacy Policy.