From 31e3aad62ab8039581d621403b7905aa19fb30af Mon Sep 17 00:00:00 2001 From: Andrey Grodzovsky Date: Thu, 25 Oct 2018 15:47:02 -0400 Subject: [PATCH] drm/amdgpu: Fix compute ring 1.0.0 failure after reset MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit 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 Acked-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 3d0f277a6523..617b0c8908a3 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4815,8 +4815,10 @@ static int gfx_v8_0_kcq_resume(struct amdgpu_device *adev) if (r) goto done; - /* Test KCQs */ - for (i = 0; i < adev->gfx.num_compute_rings; i++) { + /* Test KCQs - reversing the order of rings seems to fix ring test failure + * after GPU reset + */ + for (i = adev->gfx.num_compute_rings - 1; i >= 0; i--) { ring = &adev->gfx.compute_ring[i]; ring->ready = true; r = amdgpu_ring_test_ring(ring); -- 2.11.0