From 644baa95db2b27d4703f123d040c1d83ee058a83 Mon Sep 17 00:00:00 2001 From: Dennis Li Date: Wed, 30 Dec 2020 19:45:15 +0800 Subject: [PATCH] drm/amdgpu: fix a GPU hang issue when remove device [ Upstream commit 88e21af1b3f887d217f2fb14fc7e7d3cd87ebf57 ] When GFXOFF is enabled and GPU is idle, driver will fail to access some registers. Therefore change to disable power gating before all access registers with MMIO. Dmesg log is as following: amdgpu 0000:03:00.0: amdgpu: amdgpu: finishing device. amdgpu: cp queue pipe 4 queue 0 preemption failed amdgpu 0000:03:00.0: amdgpu: failed to write reg 2890 wait reg 28a2 amdgpu 0000:03:00.0: amdgpu: failed to write reg 1a6f4 wait reg 1a706 amdgpu 0000:03:00.0: amdgpu: failed to write reg 2890 wait reg 28a2 amdgpu 0000:03:00.0: amdgpu: failed to write reg 1a6f4 wait reg 1a706 Signed-off-by: Dennis Li Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 29141bff4b57..3b3fc9a426e9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2057,11 +2057,11 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev) if (adev->gmc.xgmi.num_physical_nodes > 1) amdgpu_xgmi_remove_device(adev); - amdgpu_amdkfd_device_fini(adev); - amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); + amdgpu_amdkfd_device_fini(adev); + /* need to disable SMC first */ for (i = 0; i < adev->num_ip_blocks; i++) { if (!adev->ip_blocks[i].status.hw)