Bug 86743

Summary: [915gm] GPU hang (page fault error)
Product: DRI Reporter: jb.1234abcd
Component: DRM/IntelAssignee: Intel GFX Bugs mailing list <intel-gfx-bugs>
Status: CLOSED WONTFIX QA Contact: Intel GFX Bugs mailing list <intel-gfx-bugs>
Severity: major    
Priority: medium CC: intel-gfx-bugs
Version: DRI git   
Hardware: x86 (IA32)   
OS: Linux (All)   
Whiteboard:
i915 platform: i915 features:
Attachments:
Description Flags
sys-class-drm-card0-error none

Description jb.1234abcd 2014-11-26 15:14:27 UTC 
Created attachment 110069 [details]
sys-class-drm-card0-error

It happens randomly.

$ journalctl
...
Nov 24 20:24:43 myhost kernel: [drm] GPU HANG: ecode -1:0x00000000, reason: Command parser error, iir 0x00008000, action: con
Nov 24 20:24:44 myhost kernel: [drm] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
Nov 24 20:24:44 myhost kernel: [drm] Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel
Nov 24 20:24:44 myhost kernel: [drm] drm/i915 developers can then reassign to the right component if it's not a kernel issue.
Nov 24 20:24:44 myhost kernel: [drm] The gpu crash dump is required to analyze gpu hangs, so please always attach it.
Nov 24 20:24:44 myhost kernel: [drm] GPU crash dump saved to /sys/class/drm/card0/error
Nov 24 20:24:44 myhost kernel: i915: render error detected, EIR: 0x00000010
Nov 24 20:24:44 myhost kernel: i915: page table error
Nov 24 20:24:44 myhost kernel: i915:   PGTBL_ER: 0x00000040
Nov 24 20:24:44 myhost kernel: [drm:i915_report_and_clear_eir] *ERROR* EIR stuck: 0x00000010, masking
Nov 24 20:24:44 myhost kernel: [drm] GPU HANG: ecode -1:0x00000000, reason: Command parser error, iir 0x00008000, action: con
Nov 24 20:24:44 myhost kernel: i915: render error detected, EIR: 0x00000010
Nov 24 20:24:44 myhost kernel: i915: page table error
Nov 24 20:24:44 myhost kernel: i915:   PGTBL_ER: 0x00000040
...

$ lspci -v
00:00.0 Host bridge: Intel Corporation Mobile 915GM/PM/GMS/910GML Express Processor to DRAM Controller (rev 03)
	Subsystem: Hewlett-Packard Company NX6110/NC6120
	Flags: bus master, fast devsel, latency 0
	Capabilities: <access denied>
	Kernel driver in use: agpgart-intel
	Kernel modules: intel_agp

00:02.0 VGA compatible controller: Intel Corporation Mobile 915GM/GMS/910GML Express Graphics Controller (rev 03) (prog-if 00 [VGA controller])
	Subsystem: Hewlett-Packard Company NX6110/NC6120
	Flags: bus master, fast devsel, latency 0, IRQ 16
	Memory at d0100000 (32-bit, non-prefetchable) [size=512K]
	I/O ports at 2000 [size=8]
	Memory at c0000000 (32-bit, prefetchable) [size=256M]
	Memory at d0180000 (32-bit, non-prefetchable) [size=256K]
	Expansion ROM at <unassigned> [disabled]
	Capabilities: <access denied>
	Kernel driver in use: i915
	Kernel modules: i915

00:02.1 Display controller: Intel Corporation Mobile 915GM/GMS/910GML Express Graphics Controller (rev 03)
	Subsystem: Hewlett-Packard Company NX6110/NC6120
	Flags: bus master, fast devsel, latency 0
	Memory at d0200000 (32-bit, non-prefetchable) [size=512K]
	Capabilities: <access denied>
...

Packages:
Linux myhost 3.17.2-1-ARCH #1 SMP PREEMPT Thu Oct 30 20:31:16 CET 2014 i686 GNU/Linux
libdrm 2.4.58-1
mesa-dri 10.3.4-1
xf86-video-intel 2.99.916-3
Comment 1 Jesse Barnes 2015-03-25 21:58:56 UTC 
Does this happen with current bits?  Does the system recover at least?
Comment 2 jb.1234abcd 2015-03-26 09:45:48 UTC 
(In reply to Jesse Barnes from comment #1)
> Does this happen with current bits?  Does the system recover at least?

It happens from time to time (Feb 18, Mar 2, Mar 12).
I do not notice it while working, just see it when I check sys logs.
Because it looks like I will not have an acces to this notebook for long time
and be able to answer relevant questions, I suggest to close this bug.

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.