Created attachment 123956 [details]
/sys/class/drm/card0/error gzip'd

I've never seen this before, and have no idea how to reproduce. Was attempting to open a new Firefox window, with the system under some I/O load (copying a DVD). Froze up for a bit, then recovered. 

Not sure if this is a useful bug report, but couldn't find any other way to submit the crash dump. I won't object at all if you close it as useless.

Linux Watt 4.4.0-1-amd64 #1 SMP Debian 4.4.6-1 (2016-03-17) x86_64 GNU/Linux
X.Org version: 1.18.2

May 21 05:30:08 Watt kernel: [drm:i915_hangcheck_elapsed [i915]] *ERROR* Hangcheck timer elapsed... render ring idle
May 21 05:31:08 Watt kernel: [drm] no progress on render ring
May 21 05:31:08 Watt kernel: [drm] GPU HANG: ecode 7:-1:0x00000000, reason: Ring hung, action: reset
May 21 05:31:08 Watt kernel: [drm] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
May 21 05:31:08 Watt kernel: [drm] Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel
May 21 05:31:08 Watt kernel: [drm] drm/i915 developers can then reassign to the right component if it's not a kernel issue.
May 21 05:31:08 Watt kernel: [drm] The gpu crash dump is required to analyze gpu hangs, so please always attach it.
May 21 05:31:08 Watt kernel: [drm] GPU crash dump saved to /sys/class/drm/card0/error
May 21 05:31:08 Watt kernel: [drm:intel_rcs_ctx_init [i915]] *ERROR* init render state: -11
May 21 05:31:08 Watt kernel: [drm:i915_switch_context [i915]] *ERROR* ring init context: -11
May 21 05:31:08 Watt kernel: drm/i915: Resetting chip after gpu hang