| Summary: | [arrandale] GPU lockup (IPEHR: 0x01820000) | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Product: | xorg | Reporter: | Bryce Harrington <bryce> | ||||||||||||
| Component: | Driver/intel | Assignee: | Chris Wilson <chris> | ||||||||||||
| Status: | RESOLVED DUPLICATE | QA Contact: | Xorg Project Team <xorg-team> | ||||||||||||
| Severity: | major | ||||||||||||||
| Priority: | high | CC: | mikael | ||||||||||||
| Version: | 7.6 (2010.12) | ||||||||||||||
| Hardware: | x86-64 (AMD64) | ||||||||||||||
| OS: | Linux (All) | ||||||||||||||
| Whiteboard: | |||||||||||||||
| i915 platform: | i915 features: | ||||||||||||||
| Attachments: |
|
||||||||||||||
|
Description
Bryce Harrington
2011-03-22 18:52:12 UTC
Created attachment 44739 [details]
i915_error_state.txt
Created attachment 44740 [details]
XorgLog.txt
Created attachment 44741 [details]
CurrentDmesg.txt
Created attachment 44742 [details]
BootDmesg.txt
Created attachment 44844 [details] [review] Scanlines are inclusive... If you can reproduce the bug, can you please try the attached patch. *** Bug 35575 has been marked as a duplicate of this bug. *** commit 972569f6fd1e14519f46e9f50d2509faf1d0aa55 Author: Chris Wilson <chris@chris-wilson.co.uk> Date: Fri Mar 25 10:46:14 2011 +0000 MI_LOAD_SCAN_LINES_INCL are inclusive and range [0, display height-1] We have seen GPU hangs with: batchbuffer at 0x0f9b4000: 0x0f9b4000: 0x09000000: MI_LOAD_SCAN_LINES_INCL 0x0f9b4004: 0x00000300: dword 1 0x0f9b4008: 0x09000000: MI_LOAD_SCAN_LINES_INCL 0x0f9b400c: 0x00000300: dword 1 0x0f9b4010: 0x01820000: MI_WAIT_FOR_EVENT 0x0f9b4014: HEAD 0x02000006: MI_FLUSH on a 1366x768 display. That according to the specs an invalid command for the pipe. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=35576 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Thanks. I prepared a package for the user to test which includes this patch. After installing and testing it, they received another crash with the same IPEHR value: i915_error_state: Time: 1301810387 s 154509 us PCI ID: 0x0046 EIR: 0x00000000 PGTBL_ER: 0x00000000 Render command stream: ACTHD: 0x006e1014 IPEIR: 0x00000000 IPEHR: 0x01820000 INSTDONE: 0xffffffff INSTDONE1: 0xbfffffff INSTPS: 0x80000020 INSTPM: 0x00000000 Full details for this new crash are here: https://bugs.launchpad.net/ubuntu/+source/xserver-xorg-video-intel/+bug/737110/+attachment/1971485/+files/xserver-xorg-video-intel.2011-04-03_07%3A59%3A49.020752.crash Hmm, might be worth testing with Option "DebugFlushCaches" "True" and/or Option "DebugFlushBatches" "True" to rule out one possibility of a bad render op that lies uncaught till the wait. No response from the reporter for testing those two options. But we've had three more bug reports come in with the same code, for various chips: 760068 [arrandale] GPU lockup (IPEHR: 0x01820000) 757399 [gm45] GPU lockup (IPEHR: 0x01820000) 752249 [q45] GPU lockup (0x01820000) Given how often we have problems with this, we should probably include the pipe/plane regs in the error_state dump so we can see whether we're waiting for scanlines that will ever change. commit c4a1d9e4dc5d5313cfec2cc0c9d630efe8a6f287 Author: Chris Wilson <chris@chris-wilson.co.uk> Date: Sun Nov 21 13:12:35 2010 +0000 drm/i915: Capture interesting display registers on error When trying to diagnose mysterious errors on resume, capture the display register contents as well. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Forward duping to the bug that has the patch... *** This bug has been marked as a duplicate of bug 36515 *** |
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.