System Environment: -------------------------- Platform: BDW Libdrm: (master)libdrm-2.4.56-8-gd9ce09de12131fa8c5ff2d7c2dbd6b61d8a5fd14 Mesa: (master)a1853eaea7fa5caf59b52567cc49f964ce5293ec Xserver: (master)xorg-server-1.15.99.902-121-g2f5cf9ff9a0f713b7e038636484c77f113a5f10a Xf86_video_intel:(master)2.99.914-60-gf5469681b620d9d6ccaf53e92ed31f931cb03b0d Libva: (master)acfcd5f0637a951d50c5112c7dfbd46f1d0dcdb3 Libva_intel_driver:(master)f3f49f2f0e6b3669d9b09341a11cf0b96e138674 Kernel: (drm-intel-nightly)49ceddc7b3b0e3f7eb21b9fb4c9b840cff630047 Bug detailed description: --------------------------- On BDW with mesa master branch, start X, then run glxgears, or run Piglit/ogles3conform/ogles2conform/ogles1conform case, X hang occurs. It works well on 10.2 branch. Bisect is in process. run glxgears output: Running synchronized to the vertical refresh. The framerate should be approximately the same as the monitor refresh rate. intel_do_flush_locked failed: Input/output error dmesg [ 298.895715] [drm] stuck on render ring [ 298.896666] [drm] GPU HANG: ecode 0:0x87949ff9, in X [4431], reason: Ring hung, action: reset [ 298.896668] [drm] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace. [ 298.896669] [drm] Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel [ 298.896671] [drm] drm/i915 developers can then reassign to the right component if it's not a kernel issue. [ 298.896672] [drm] The gpu crash dump is required to analyze gpu hangs, so please always attach it. [ 298.896673] [drm] GPU crash dump saved to /sys/class/drm/card0/error [ 298.896756] [drm:i915_error_work_func] resetting chip [ 298.898723] [drm:init_status_page] render ring hws offset: 0x007fb000 [ 298.898737] [drm:init_status_page] bsd ring hws offset: 0x0081d000 [ 298.898746] [drm:init_status_page] blitter ring hws offset: 0x0083e000 [ 298.898753] [drm:init_status_page] video enhancement ring hws offset: 0x0085f000 [ 298.898788] [drm:ironlake_update_primary_plane] Writing base 00000000 00000000 0 0 7680 [ 300.896739] [drm:intel_print_rc6_info] Enabling RC6 states: RC6 on, RC6p off, RC6pp off [ 304.898807] [drm] stuck on render ring [ 304.899776] [drm] GPU HANG: ecode 0:0xf3cffffe, in X [4431], reason: Ring hung, action: reset [ 304.899863] [drm:i915_error_work_func] resetting chip [ 304.901815] [drm:init_status_page] render ring hws offset: 0x007fb000 [ 304.901829] [drm:init_status_page] bsd ring hws offset: 0x0081d000 [ 304.901838] [drm:init_status_page] blitter ring hws offset: 0x0083e000 [ 304.901846] [drm:init_status_page] video enhancement ring hws offset: 0x0085f000 [ 304.901881] [drm:ironlake_update_primary_plane] Writing base 00000000 00000000 0 0 7680 [ 306.899854] [drm:intel_print_rc6_info] Enabling RC6 states: RC6 on, RC6p off, RC6pp off Reproduce steps: ---------------------------- 1. xinit 2. glxgears
Bisect shows: 45eb06566830eb49551c27262cdd936bf42ec922 is the first bad commit commit 45eb06566830eb49551c27262cdd936bf42ec922 Author: Matt Turner <mattst88@gmail.com> AuthorDate: Sun Aug 17 00:45:27 2014 -0700 Commit: Matt Turner <mattst88@gmail.com> CommitDate: Mon Aug 18 18:18:50 2014 -0700 i965: Enable instruction compaction on Gen8+. Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
*** This bug has been marked as a duplicate of bug 82846 ***
Verified.Fixed.
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.