[PATCH v3] drm/amdgpu: Call amdgpu_device_unmap_mmio() if device is unplugged to prevent crash in GPU initialization failure

[Andrey Grodzovsky]

Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky at amd.com>

Andrey

On 2021-12-17 3:49 a.m., Christian König wrote:
> Am 17.12.21 um 03:26 schrieb Leslie Shi:
>> [Why]
>> In amdgpu_driver_load_kms, when amdgpu_device_init returns error 
>> during driver modprobe, it
>> will start the error handle path immediately and call into 
>> amdgpu_device_unmap_mmio as well
>> to release mapped VRAM. However, in the following release callback, 
>> driver stills visits the
>> unmapped memory like vcn.inst[i].fw_shared_cpu_addr in 
>> vcn_v3_0_sw_fini. So a kernel crash occurs.
>>
>> [How]
>> call amdgpu_device_unmap_mmio() if device is unplugged to prevent 
>> invalid memory address in
>> vcn_v3_0_sw_fini() when GPU initialization failure.
>>
>> Signed-off-by: Leslie Shi <Yuliang.Shi at amd.com>
>
> Looks sane to me, but Andrey should probably nood as well.
>
> Acked-by: Christian König <christian.koenig at amd.com>
>
>> ---
>>   drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 +++-
>>   1 file changed, 3 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c 
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> index f31caec669e7..f6a47b927cfd 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> @@ -3899,7 +3899,9 @@ void amdgpu_device_fini_hw(struct amdgpu_device 
>> *adev)
>>         amdgpu_gart_dummy_page_fini(adev);
>>   -    amdgpu_device_unmap_mmio(adev);
>> +    if (drm_dev_is_unplugged(adev_to_drm(adev)))
>> +        amdgpu_device_unmap_mmio(adev);
>> +
>>   }
>>     void amdgpu_device_fini_sw(struct amdgpu_device *adev)
>