[Bug 95512] New: random GPU hangs on normal desktop usage

[bugzilla-daemon at freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=95512

            Bug ID: 95512
           Summary: random GPU hangs on normal desktop usage
           Product: DRI
           Version: unspecified
          Hardware: x86-64 (AMD64)
                OS: Linux (All)
            Status: NEW
          Severity: normal
          Priority: medium
         Component: DRM/Intel
          Assignee: intel-gfx-bugs at lists.freedesktop.org
          Reporter: freedesktop at chris.ielf.org
        QA Contact: intel-gfx-bugs at lists.freedesktop.org
                CC: intel-gfx-bugs at lists.freedesktop.org

Created attachment 123946
  --> https://bugs.freedesktop.org/attachment.cgi?id=123946&action=edit
GPU crash dump

Hi

On Manjaro up-to-date (16.06-rc1) i randomly have frozen desktop for a few
seconds, sometime almost a minute. It happen every few days.

I had the same kind of problem with ArchLinux (up to date too) previously with
last 4.4 kernels (standard & lts)

I'm running an XPS 13 9343 so thats an i7-5500U
00:02.0 VGA compatible controller: Intel Corporation Broadwell-U Integrated
Graphics (rev 09)

Last freeze gave some output in logs and a GPU crash dump:

[ 1218.317218] [drm] stuck on render ring
[ 1218.318228] [drm] GPU HANG: ecode 8:0:0x85dffffb, in Xorg [995], reason:
Ring hung, action: reset
[ 1218.318230] [drm] GPU hangs can indicate a bug anywhere in the entire gfx
stack, including userspace.
[ 1218.318231] [drm] Please file a _new_ bug report on bugs.freedesktop.org
against DRI -> DRM/Intel
[ 1218.318231] [drm] drm/i915 developers can then reassign to the right
component if it's not a kernel issue.
[ 1218.318232] [drm] The gpu crash dump is required to analyze gpu hangs, so
please always attach it.
[ 1218.318233] [drm] GPU crash dump saved to /sys/class/drm/card0/error
[ 1218.320369] drm/i915: Resetting chip after gpu hang
[ 1224.322112] [drm] stuck on render ring
[ 1224.323098] [drm] GPU HANG: ecode 8:0:0x85dffffb, in Xorg [995], reason:
Ring hung, action: reset
[ 1224.323192] [drm:i915_set_reset_status [i915]] *ERROR* gpu hanging too fast,
banning!
[ 1224.325284] drm/i915: Resetting chip after gpu hang


It was running on:
xtra intel-ucode 20151106-1 [installed]
extra xf86-video-intel 1:2.99.917+641+ge4ef6e9-0.1 [installed]
extra xorg-server 1.17.4-2 [installed]
Standard kernel 4.1.24-1-MANJARO


My issue seems very similar to 94599

-- 
You are receiving this mail because:
You are the QA Contact for the bug.
You are the assignee for the bug.
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/intel-gfx-bugs/attachments/20160521/5c6dd1f7/attachment.html>