Do RAS page retirement and use gpu reset as fallback in UTCL2 fault
handler.
v2: replace vm fault event with posion consumed event in UTCL2
poison consumption.
Signed-off-by: Tao Zhou <tao.zh...@amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index e5f03f79546f..55ee062a8496 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -312,6 +312,12 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev,
struct kfd_vm_fault_info info = {0};
uint16_t ring_id = SOC15_RING_ID_FROM_IH_ENTRY(ih_ring_entry);
+ if (client_id == SOC15_IH_CLIENTID_UTCL2 &&
+ amdgpu_amdkfd_ras_query_utcl2_poison_status(dev->adev)) {
+ event_interrupt_poison_consumption(dev, pasid,
client_id);
+ return;
+ }
+
info.vmid = vmid;
info.mc_id = client_id;
info.page_addr = ih_ring_entry[4] |
--
2.35.1
