[Bug 88565] New: [IVB] GPU HANG: ecode 0:0x85fffffc, in Gw2.exe

[bugzilla-daemon at freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=88565

            Bug ID: 88565
           Summary: [IVB] GPU HANG: ecode 0:0x85fffffc, in Gw2.exe
           Product: DRI
           Version: unspecified
          Hardware: Other
                OS: All
            Status: NEW
          Severity: normal
          Priority: medium
         Component: DRM/Intel
          Assignee: intel-gfx-bugs at lists.freedesktop.org
          Reporter: bugzilla at dolphinling.net
        QA Contact: intel-gfx-bugs at lists.freedesktop.org
                CC: intel-gfx-bugs at lists.freedesktop.org

Created attachment 112439
  --> https://bugs.freedesktop.org/attachment.cgi?id=112439&action=edit
/sys/class/drm/card0/error

When playing Guild Wars 2 through Wine, I get an occasional gpu hang
(manifesting in game as the screen not updating for a few seconds, though
sounds continue to play). Usually, the gpu resets and everything works again,
but sometimes it doesn't reset properly. Those times, nothing I do seems to
change the output on that VT, though switching to a different VT still works
and restarting GDM does clear out the broken VT for reuse.

Gentoo
Linux 3.18.3
Mesa git
libdrm 2.4.58
xorg-server 1.16.3
wine 1.7.34


dmesg:
[70851.279605] [drm] stuck on render ring
[70851.280347] [drm] GPU HANG: ecode 0:0x85fffffc, in Gw2.exe [4480], reason:
Ring hung, action: reset
[70851.280349] [drm] GPU hangs can indicate a bug anywhere in the entire gfx
stack, including userspace.
[70851.280350] [drm] Please file a _new_ bug report on bugs.freedesktop.org
against DRI -> DRM/Intel
[70851.280351] [drm] drm/i915 developers can then reassign to the right
component if it's not a kernel issue.
[70851.280352] [drm] The gpu crash dump is required to analyze gpu hangs, so
please always attach it.
[70851.280353] [drm] GPU crash dump saved to /sys/class/drm/card0/error
[72161.004531] [drm] stuck on render ring
[72161.005335] [drm] GPU HANG: ecode 0:0x85fffffd, in Gw2.exe [4480], reason:
Ring hung, action: reset
[78324.054877] [drm] stuck on render ring
[78324.055603] [drm] GPU HANG: ecode 0:0x85ffbff8, in Gw2.exe [4480], reason:
Ring hung, action: reset
[79728.676207] [drm] stuck on render ring
[79728.677056] [drm] GPU HANG: ecode 0:0x85ff9ff8, in Gw2.exe [4480], reason:
Ring hung, action: reset
[80234.207221] [drm] stuck on render ring
[80234.207993] [drm] GPU HANG: ecode 0:0x85ffbff8, in Gw2.exe [4480], reason:
Ring hung, action: reset
[103135.056777] [drm] stuck on render ring
[103135.057490] [drm] GPU HANG: ecode 0:0x85fffffc, in Gw2.exe [7780], reason:
Ring hung, action: reset
[103137.056835] ------------[ cut here ]------------
[103137.056862] WARNING: CPU: 2 PID: 113 at
drivers/gpu/drm/i915/intel_pm.c:3661 gen6_enable_rps_interrupts+0x6a/0x70()
[103137.056864] Modules linked in: snd_seq_midi snd_emu10k1_synth
snd_emux_synth snd_seq_midi_emul snd_seq_virmidi snd_seq_midi_event snd_seq
af_packet usb_storage hid_generic usbhid hid coretemp hwmon snd_hda_codec_hdmi
snd_hda_codec_realtek snd_hda_codec_generic snd_emu10k1 x86_pkg_temp_thermal
snd_hwdep snd_util_mem crc32c_intel snd_ac97_codec ac97_bus snd_rawmidi r8169
snd_seq_device mii xhci_pci xhci_hcd ehci_pci ehci_hcd thermal snd_hda_intel
snd_hda_controller snd_hda_codec snd_pcm rtc_cmos snd_timer usbcore snd
soundcore evdev usb_common i2c_i801 processor fan ipv6 autofs4
[103137.056914] CPU: 2 PID: 113 Comm: kworker/2:1 Not tainted 3.18.3 #3
[103137.056917] Hardware name: System manufacturer System Product Name/P8Z77-V
LK, BIOS 0210 03/12/2012
[103137.056922] Workqueue: events intel_gen6_powersave_work
[103137.056924]  0000000000000009 ffff88040c797d28 ffffffff814ed167
0000000000000000
[103137.056929]  0000000000000000 ffff88040c797d68 ffffffff81043edc
0000000000000007
[103137.056933]  ffff88040cdc0000 ffff88040cd99000 ffff88040cdc8690
0000000000060000
[103137.056937] Call Trace:
[103137.056943]  [<ffffffff814ed167>] dump_stack+0x46/0x58
[103137.056949]  [<ffffffff81043edc>] warn_slowpath_common+0x7c/0xa0
[103137.056953]  [<ffffffff81043fa5>] warn_slowpath_null+0x15/0x20
[103137.056957]  [<ffffffff813541da>] gen6_enable_rps_interrupts+0x6a/0x70
[103137.056961]  [<ffffffff8135ca61>] intel_gen6_powersave_work+0x5b1/0x1060
[103137.056967]  [<ffffffff81059c58>] process_one_work+0x148/0x3d0
[103137.056970]  [<ffffffff81059ff9>] worker_thread+0x119/0x480
[103137.056974]  [<ffffffff81059ee0>] ? process_one_work+0x3d0/0x3d0
[103137.056979]  [<ffffffff8105e974>] kthread+0xc4/0xe0
[103137.056983]  [<ffffffff8105e8b0>] ? kthread_create_on_node+0x180/0x180
[103137.056988]  [<ffffffff814f2fac>] ret_from_fork+0x7c/0xb0
[103137.056992]  [<ffffffff8105e8b0>] ? kthread_create_on_node+0x180/0x180
[103137.056995] ---[ end trace 770645c6e2c851ed ]---
[103140.044207] [drm:i915_hangcheck_elapsed] *ERROR* Hangcheck timer elapsed...
render ring idle

-- 
You are receiving this mail because:
You are the QA Contact for the bug.
You are on the CC list for the bug.
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.freedesktop.org/archives/intel-gfx-bugs/attachments/20150118/67c16070/attachment.html>