Bug 97128

Summary: Kernel hang when running out of memory
Product: DRI Reporter: Bas Nieuwenhuizen <bas>
Component: DRM/AMDgpuAssignee: Default DRI bug account <dri-devel>
Status: RESOLVED FIXED QA Contact:
Severity: normal    
Priority: medium    
Version: XOrg git   
Hardware: Other   
OS: All   
Whiteboard:
i915 platform: i915 features:

Description Bas Nieuwenhuizen 2016-07-29 11:09:17 UTC 
If I allocate too much memory I get a kernel hang using the drm-next-4.8 branch from Alex Deucher. SSH stops working too.

This has been tests by allocating GTT buffers in a loop using the winsys for the new radv vulkan driver. Just as radeonsi, the winsys has a 3 step allocation process: 1) allocate the buffer 2) Allocate an address range 3) Map the buffer to address range.

This hang is a regression. Bisection pointed to the following patch as culprit:

commit 089f16c55baacd5e8ae3745625efa82899b4b217
Author: Christian König <christian.koenig@amd.com>
Date:   Mon Jun 6 10:17:50 2016 +0200

    drm/ttm: cleanup ttm_tt_(unbind|destroy)
    
    ttm_tt_destroy should be the only one unbinding the object.
    
    Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
    Signed-off-by: Christian König <christian.koenig@amd.com>
    Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Comment 1 Alex Deucher 2016-07-29 14:17:38 UTC 
Should be fixed in this patch:
https://lists.freedesktop.org/archives/amd-gfx/2016-July/000686.html
Comment 2 Bas Nieuwenhuizen 2016-07-29 14:35:49 UTC 
I can confirm that patch fixes the hang for me.

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.