linux-kernel - [2.6.38-rc6] G965: i915 Hangcheck timer elapsed... GPU hung (not reproducible)

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Date:	Sun, 27 Feb 2011 10:10:41 +0100
From:	Paolo Ornati <ornati@...il.com>
To:	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: [2.6.38-rc6] G965: i915 Hangcheck timer elapsed... GPU hung (not
 reproducible)

Today I got this while starting a video in SMplayer (MPlayer) with
2.6.38-rc6-00113-g4662db4:

[  830.880014] [drm:i915_hangcheck_elapsed] *ERROR* Hangcheck timer elapsed... GPU hung
[  830.880736] [drm:i915_do_wait_request] *ERROR* i915_do_wait_request returns -11 (awaiting 174895 at 174857, next 174896)
[  830.881093] [drm:init_ring_common] *ERROR* render ring initialization failed ctl 00000000 head 00000000 tail 00000000 start 00000000
[  831.379079] [drm:i915_do_wait_request] *ERROR* something (likely vbetool) disabled interrupts, re-enabling
[  831.399099] [drm:i915_do_wait_request] *ERROR* something (likely vbetool) disabled interrupts, re-enabling
	...
[  837.392012] [drm:i915_hangcheck_elapsed] *ERROR* Hangcheck timer elapsed... GPU hung
[  837.392038] [drm:i915_do_wait_request] *ERROR* i915_do_wait_request returns -11 (awaiting 175016 at 174857, next 175022)
[  837.392491] [drm:init_ring_common] *ERROR* render ring initialization failed ctl 00000000 head 00000000 tail 00000000 start 00000000
[  837.537479] [drm:i915_do_wait_request] *ERROR* something (likely vbetool) disabled interrupts, re-enabling
[  837.543285] [drm:i915_do_wait_request] *ERROR* something (likely vbetool) disabled interrupts, re-enabling
	...
[  839.040011] [drm:i915_hangcheck_elapsed] *ERROR* Hangcheck timer elapsed... GPU hung
[  839.040034] [drm:i915_do_wait_request] *ERROR* i915_do_wait_request returns -11 (awaiting 175022 at 174857, next 175122)
[  839.040364] [drm:i915_reset] *ERROR* GPU hanging too fast, declaring wedged!
[  839.040367] [drm:i915_reset] *ERROR* Failed to reset chip.

Screen was almost freezed, cursor was stuck but the machine was alive
and I was able to use SysRq to kill X and try to restart it (but that
didn't help).

I don't remember anything similar in recent kernels (<= 2.6.37) and got
this only once with 2.6.38-rcX.

Environment at the time of the GPU crash:
	KDE4 (without "Desktop Effects")
	Chromium
	Claws Mail
	Dolphin
	ccached make -j3 on a just pulled linux-tree (so I/O bound)
	SMPlayer/Mplayer (just launched)

Assorted logs attached.

Bye,

-- 
	Paolo Ornati
	Linux 2.6.38-rc6-00113-g4662db4 on x86_64

Download attachment "config" of type "application/octet-stream" (59329 bytes)

Download attachment "dmesg" of type "application/octet-stream" (127271 bytes)

Download attachment "lspci" of type "application/octet-stream" (2078 bytes)

Download attachment "normal-dmesg" of type "application/octet-stream" (46056 bytes)

View attachment "Xorg.log" of type "text/x-log" (18197 bytes)