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@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 17 ++++++++++++++---
1 file changed, 14 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 474f8ea58aa5..7b07af1873bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4284,6 +4284,7 @@ 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);
@@ -4312,9 +4313,19 @@ 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) {
--
2.17.1
