drm/amdgpu: recover XGMI topology for SRIOV VF after reset

For SRIOV VF, the XGMI topology was not recovered after reset. This
change added code to SRIOV VF reset function to update XGMI topology
for SRIOV VF after reset.

Signed-off-by: Zhigang Luo <zhigang.luo@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 25a9e52..262a6b6 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4285,6 +4285,7 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
                                     bool from_hypervisor)
 {
        int r;
+       struct amdgpu_hive_info *hive = NULL;
 
        amdgpu_amdkfd_pre_reset(adev);
 
@@ -4313,9 +4314,19 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
        if (r)
                goto error;
 
-       amdgpu_irq_gpu_reset_resume_helper(adev);
-       r = amdgpu_ib_ring_tests(adev);
-       amdgpu_amdkfd_post_reset(adev);
+       hive = amdgpu_get_xgmi_hive(adev);
+       /* Update PSP FW topology after reset */
+       if (hive && adev->gmc.xgmi.num_physical_nodes > 1)
+               r = amdgpu_xgmi_update_topology(hive, adev);
+
+       if (hive)
+               amdgpu_put_xgmi_hive(hive);
+
+       if (!r) {
+               amdgpu_irq_gpu_reset_resume_helper(adev);
+               r = amdgpu_ib_ring_tests(adev);
+               amdgpu_amdkfd_post_reset(adev);
+       }
 
 error:
        if (!r && adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {