XGMI support is more complicated than single device support as
questions of synchronization between the device recovering from
PCI error and other members of the hive are required.
Leaving this for next round.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@xxxxxxx>
Reviewed-by: Alex Deucher <alexander.deucher@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c477cfd..4d4fc67 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4778,6 +4778,11 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
DRM_INFO("PCI error: detected callback, state(%d)!!\n", state);
+ if (adev->gmc.xgmi.num_physical_nodes > 1) {
+ DRM_WARN("No support for XGMI hive yet...");
+ return PCI_ERS_RESULT_DISCONNECT;
+ }
+
switch (state) {
case pci_channel_io_normal:
return PCI_ERS_RESULT_CAN_RECOVER;
--
2.7.4
