Bug 85944 - [945gme] Display B: Invalid tiling
Summary: [945gme] Display B: Invalid tiling
Status: CLOSED WONTFIX
Alias: None
Product: DRI
Classification: Unclassified
Component: DRM/Intel (show other bugs)
Version: unspecified
Hardware: x86 (IA32) Linux (All)
: medium minor
Assignee: Intel GFX Bugs mailing list
QA Contact: Intel GFX Bugs mailing list
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2014-11-05 22:44 UTC by Anonymous Helper
Modified: 2017-07-24 22:50 UTC (History)
1 user (show)

See Also:
i915 platform:
i915 features:


Attachments
/sys/class/drm/card0/error.xz (34.75 KB, application/x-xz)
2014-11-05 22:44 UTC, Anonymous Helper
no flags Details

Description Anonymous Helper 2014-11-05 22:44:28 UTC
Created attachment 108995 [details]
/sys/class/drm/card0/error.xz

[42969.772395] [drm] GPU HANG: ecode -1:0x00000000, reason: Command parser error, iir 0x00008000, action: continue
[42969.772395] [drm] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
[42969.772395] [drm] Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel
[42969.772395] [drm] drm/i915 developers can then reassign to the right component if it's not a kernel issue.
[42969.772395] [drm] The gpu crash dump is required to analyze gpu hangs, so please always attach it.
[42969.772395] [drm] GPU crash dump saved to /sys/class/drm/card0/error
[42969.772395] i915: render error detected, EIR: 0x00000010
[42969.772395] i915: page table error
[42969.772395] i915:   PGTBL_ER: 0x00000400
[42969.772395] [drm:i915_report_and_clear_eir] *ERROR* EIR stuck: 0x00000010, masking
[42969.772395] [drm] GPU HANG: ecode -1:0x00000000, reason: Command parser error, iir 0x00008000, action: continue
[42969.772395] i915: render error detected, EIR: 0x00000010
[42969.772395] i915: page table error
[42969.772395] i915:   PGTBL_ER: 0x00000400


All I noticed was a jerky mouse

xorg-server 1.16.1-1
xf86-video-intel 2.99.916-3
dri2proto 2.8-2
dri3proto 1.0-1
mesa 10.3.2-1
mesa-dri 10.3.2-1
Comment 1 Chris Wilson 2014-11-06 07:33:10 UTC
As usual, Display B is nowhere near a Y-fence.

Interestingly though:

  05400000  4194304 40 40 0 0 P Y dirty uncached (fence: 5)

i.e. at the time of the error, the only Y-fenced surface is being accessed (it is currently pinned for use in the hardware) which implies that we are servicing i915_gem_fault(). Impression remains that this is the hardware crying wolf.
Comment 2 Daniel Vetter 2014-11-24 21:10:00 UTC
Ok, invalid tiling hangs seem to be mostly red herrings, so let's close them. Also recent kernels wont' report them any more - recent = 3.19 or so ;-)

commit 4f15a1a098745ef0cc496256ec14bd31e0d82683
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date:   Tue Nov 4 15:52:22 2014 +0100

    drm/i915: Stop gathering error states for CS error interrupts

Thanks anyway for reporting this issue.


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.