drm/amdgpu: kfd_pre_reset outside req_full_gpu cause sriov hang

XGMI hive put kfd_pre_reset into amdgpu_device_lock_adev,
but outside req_full_gpu of sriov.
It would make sriov hang during reset.

Signed-off-by: Wentao Lou <Wentao.Lou@amd.com>
Reviewed-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b60afeade50a3f86db57c26f993f2aacedd1c71e..8a078f4ae73dd17cc43384e605d28e4c613e7c37 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3476,14 +3476,16 @@ static void amdgpu_device_lock_adev(struct amdgpu_device *adev)
        mutex_lock(&adev->lock_reset);
        atomic_inc(&adev->gpu_reset_counter);
        adev->in_gpu_reset = 1;
-       /* Block kfd */
-       amdgpu_amdkfd_pre_reset(adev);
+       /* Block kfd: SRIOV would do it separately */
+       if (!amdgpu_sriov_vf(adev))
+                amdgpu_amdkfd_pre_reset(adev);
 }
 
 static void amdgpu_device_unlock_adev(struct amdgpu_device *adev)
 {
-       /*unlock kfd */
-       amdgpu_amdkfd_post_reset(adev);
+       /*unlock kfd: SRIOV would do it separately */
+       if (!amdgpu_sriov_vf(adev))
+                amdgpu_amdkfd_post_reset(adev);
        amdgpu_vf_error_trans_all(adev);
        adev->in_gpu_reset = 0;
        mutex_unlock(&adev->lock_reset);