[Bug 63748] New: GPU Lockup playing urban terror

[bugzilla-daemon at freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=63748

          Priority: medium
            Bug ID: 63748
          Assignee: dri-devel at lists.freedesktop.org
           Summary: GPU Lockup playing urban terror
          Severity: major
    Classification: Unclassified
                OS: Linux (All)
          Reporter: dinolib at libero.it
          Hardware: x86-64 (AMD64)
            Status: NEW
           Version: XOrg CVS
         Component: DRM/Radeon
           Product: DRI

Playing UrT just few minutes, bring to CPU lockup rescued in some seconds with
a softreset. Sometimes the system can't recover from this state.

Before Mesa 9 (and relative dri drivers) update never happened.

01:05.0 VGA compatible controller: Advanced Micro Devices [AMD] nee ATI RS880M
[Mobility Radeon HD 4200 Series]

Kernel 3.7.6 (Chakra linux)

Environment: KDE (both OpenGL and XRender)

Tested with any kind of radeon power management (dynamic, high and low
profile).

dmesg log:

[646081.016040] radeon 0000:01:05.0: GPU lockup CP stall for more than
10000msec
[646081.016048] radeon 0000:01:05.0: GPU lockup (waiting for 0x00000000003b66b2
last fence id 0x00000000003b66ac)
[646081.017095] radeon 0000:01:05.0: Saved 185 dwords of commands on ring 0.
[646081.017099] radeon 0000:01:05.0: GPU softreset 
[646081.017102] radeon 0000:01:05.0:   R_008010_GRBM_STATUS=0xA00024AC
[646081.017104] radeon 0000:01:05.0:   R_008014_GRBM_STATUS2=0x00000003
[646081.017106] radeon 0000:01:05.0:   R_000E50_SRBM_STATUS=0x20000040
[646081.017109] radeon 0000:01:05.0:   R_008674_CP_STALLED_STAT1 = 0x04000000
[646081.017111] radeon 0000:01:05.0:   R_008678_CP_STALLED_STAT2 = 0x00040002
[646081.017114] radeon 0000:01:05.0:   R_00867C_CP_BUSY_STAT     = 0x00008484
[646081.017116] radeon 0000:01:05.0:   R_008680_CP_STAT          = 0x80858645
[646081.017122] radeon 0000:01:05.0:   R_008020_GRBM_SOFT_RESET=0x00007FEE
[646081.032099] radeon 0000:01:05.0: R_008020_GRBM_SOFT_RESET=0x00000001
[646081.048074] radeon 0000:01:05.0:   R_008010_GRBM_STATUS=0xA0003030
[646081.048077] radeon 0000:01:05.0:   R_008014_GRBM_STATUS2=0x00000003
[646081.048079] radeon 0000:01:05.0:   R_000E50_SRBM_STATUS=0x20008040
[646081.048082] radeon 0000:01:05.0:   R_008674_CP_STALLED_STAT1 = 0x00000000
[646081.048084] radeon 0000:01:05.0:   R_008678_CP_STALLED_STAT2 = 0x00000000
[646081.048086] radeon 0000:01:05.0:   R_00867C_CP_BUSY_STAT     = 0x00000000
[646081.048089] radeon 0000:01:05.0:   R_008680_CP_STAT          = 0x80100000
[646081.049090] radeon 0000:01:05.0: GPU reset succeeded, trying to resume
[646081.053294] [drm] PCIE GART of 512M enabled (table at 0x00000000C0040000).
[646081.053366] radeon 0000:01:05.0: WB enabled
[646081.053370] radeon 0000:01:05.0: fence driver on ring 0 use gpu addr
0x00000000a0000c00 and cpu addr 0xffff8800c884dc00
[646081.053639] radeon 0000:01:05.0: setting latency timer to 64
[646081.085618] [drm] ring test on 0 succeeded in 0 usecs
[646081.094844] [drm] ib test on ring 0 succeeded in 0 usecs

No errors in Xorg.log

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.freedesktop.org/archives/dri-devel/attachments/20130420/8fd463f4/attachment.html>