drm/amdgpu: Fix compute ring 1.0.0 failure after reset
authorAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Thu, 25 Oct 2018 19:47:02 +0000 (15:47 -0400)
committerAlex Deucher <alexander.deucher@amd.com>
Fri, 26 Oct 2018 18:27:30 +0000 (13:27 -0500)
commit31e3aad62ab8039581d621403b7905aa19fb30af
treeac2573dcf20c3c9b121b66c269fc69fb1f0af23b
parent4faaaa762328cfb8579b9c908999ca189e2ea474
drm/amdgpu: Fix compute ring 1.0.0 failure after reset

Problem: After GPU reset on dGPUs with gfx8 compute ring
1.0.0 fails to pass the ring test. Ring registers inspection
shows that it's active and no hang is observed (rptr == wptr)
No significant diffs were observed between CP_HQD* registers
for the ring in good and bad shape.

Fix: No clear reason why but reversing the order of ring tests
fixes the problem.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c