[PATCH] drm/amdgpu/gfx9.4.3: Explicitly halt MEC before init

Alex Deucher alexander.deucher at amd.com
Thu Sep 12 23:29:24 UTC 2024


Need to make sure it's halted as we don't know what state
the GPU may have been left in previously.

Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 611659404703..c100845409f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -2248,6 +2248,8 @@ static int gfx_v9_4_3_xcc_cp_resume(struct amdgpu_device *adev, int xcc_id)
 		r = gfx_v9_4_3_xcc_cp_compute_load_microcode(adev, xcc_id);
 		if (r)
 			return r;
+	} else {
+		gfx_v9_4_3_xcc_cp_compute_enable(adev, false, xcc_id);
 	}
 
 	r = gfx_v9_4_3_xcc_kiq_resume(adev, xcc_id);
-- 
2.46.0



More information about the amd-gfx mailing list