drm/amdgpu: make sure retry faults are handled in a work item on Vega
authorChristian König <christian.koenig@amd.com>
Sat, 31 Oct 2020 17:46:59 +0000 (18:46 +0100)
committerAlex Deucher <alexander.deucher@amd.com>
Tue, 24 Nov 2020 17:06:49 +0000 (12:06 -0500)
commit0291150d3c618712337931bf26ef758f944aa32c
tree2f2c5a4288d31d2882feb18d03efe6676685cee7
parent4750918978a7829954a248da0b964f36740299b5
drm/amdgpu: make sure retry faults are handled in a work item on Vega

Looks like we can't enabled the IH1/IH2 feature for Vega20, make sure
retry faults are handled on a separate ring anyway.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c