[PATCH 2/2] drm/amdgpu: should stop GFX ring in hw_fini

Monk Liu Monk.Liu at amd.com
Fri Nov 29 08:23:32 UTC 2019


To align with the scheme from gfx9:

without disabling gfx ring in hw_fini we would
hit GFX hang if a guest VM is destroyed suddenly
when running a game

Signed-off-by: Monk Liu <Monk.Liu at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 230e8af..882cf1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3809,6 +3809,7 @@ static int gfx_v10_0_hw_fini(void *handle)
 	if (amdgpu_gfx_disable_kcq(adev))
 		DRM_ERROR("KCQ disable failed\n");
 	if (amdgpu_sriov_vf(adev)) {
+		gfx_v10_0_cp_gfx_enable(adev, false);
 		pr_debug("For SRIOV client, shouldn't do anything.\n");
 		return 0;
 	}
-- 
2.7.4



More information about the amd-gfx mailing list