Bug 66964

Summary: GPU VM faults on ARUBA
Product: Mesa Reporter: udo <udovdh>
Component: Drivers/Gallium/r600Assignee: Default DRI bug account <dri-devel>
Status: RESOLVED MOVED QA Contact:
Severity: normal    
Priority: medium CC: otaznik
Version: git   
Hardware: Other   
OS: All   
Whiteboard:
i915 platform: i915 features:

Description udo 2013-07-16 14:12:23 UTC
Hello,

See https://bugs.freedesktop.org/show_bug.cgi?id=62959 as reference.
I turned off RADEON_VA=0 and R600_DEBUG=nodma and after a while I got the output below (and a reboot) while surfing the web, checking videos from youtube, etc. I use git everything on A10-5800K which has ARUBA (Cayman) GPU with kernel.org 3.9.9.
What is the cause? And how can we fix this?


Jul 16 16:00:01 surfplank2 kernel: [178650.498628] radeon 0000:00:01.0: GPU fault detected: 147 0x0db67102
Jul 16 16:00:01 surfplank2 kernel: [178650.498633] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00001EDB
Jul 16 16:00:01 surfplank2 kernel: [178650.498635] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x06071002
Jul 16 16:00:01 surfplank2 kernel: [178650.498638] radeon 0000:00:01.0: GPU fault detected: 147 0x0db67102
Jul 16 16:00:01 surfplank2 kernel: [178650.498640] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498643] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498645] radeon 0000:00:01.0: GPU fault detected: 146 0x01f67104
Jul 16 16:00:01 surfplank2 kernel: [178650.498647] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498649] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498652] radeon 0000:00:01.0: GPU fault detected: 146 0x02067104
Jul 16 16:00:01 surfplank2 kernel: [178650.498654] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498656] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498658] radeon 0000:00:01.0: GPU fault detected: 146 0x02067104
Jul 16 16:00:01 surfplank2 kernel: [178650.498660] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498662] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498664] radeon 0000:00:01.0: GPU fault detected: 147 0x03b67102
Jul 16 16:00:01 surfplank2 kernel: [178650.498667] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498669] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498671] radeon 0000:00:01.0: GPU fault detected: 147 0x03c67102
Jul 16 16:00:01 surfplank2 kernel: [178650.498673] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498675] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498677] radeon 0000:00:01.0: GPU fault detected: 147 0x03c67102
Jul 16 16:00:01 surfplank2 kernel: [178650.498679] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498681] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498683] radeon 0000:00:01.0: GPU fault detected: 147 0x03c67102
Jul 16 16:00:01 surfplank2 kernel: [178650.498685] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498687] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498690] radeon 0000:00:01.0: GPU fault detected: 146 0x02067104
Jul 16 16:00:01 surfplank2 kernel: [178650.498692] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498694] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x06071004
Jul 16 16:00:01 surfplank2 kernel: [178650.498711] radeon 0000:00:01.0: GPU fault detected: 146 0x09767104
Jul 16 16:00:01 surfplank2 kernel: [178650.498713] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x00000000
Jul 16 16:00:01 surfplank2 kernel: [178650.498715] radeon 0000:00:01.0:   VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x00000000

Kind regards,
Udo
Comment 1 Alex Deucher 2013-07-16 15:24:44 UTC
Are things improved any with Dave's drm-fixes tree:
http://cgit.freedesktop.org/~airlied/linux/log/?h=drm-fixes
It contains some alignment fixes for VM that may help and it should provide better debugging output of the VM faults.
Comment 2 GitLab Migration User 2019-09-18 19:04:58 UTC
-- GitLab Migration Automatic Message --

This bug has been migrated to freedesktop.org's GitLab instance and has been closed from further activity.

You can subscribe and participate further through the new bug through this link to our GitLab instance: https://gitlab.freedesktop.org/mesa/mesa/issues/453.

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.