[PATCH 1/3] drm/amdkfd: Check int source id for utcl2 poison event

Hawking Zhang Hawking.Zhang at amd.com
Mon Aug 19 15:14:35 UTC 2024


Traditional utcl2 fault_status polling does not
work in SRIOV environment. The polling of fault
status register from guest side will be dropped
by hardware.

Driver should switch to check utcl2 interrupt
source id to identify utcl2 poison event. It is
set to 1 when poisoned data interrupts are
signaled.

Signed-off-by: Hawking Zhang <Hawking.Zhang at amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c | 3 +--
 drivers/gpu/drm/amd/amdkfd/soc15_int.h          | 1 +
 2 files changed, 2 insertions(+), 2 deletions(-)

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 a9c3580be8c9..1196dccbe6bc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -448,8 +448,7 @@ static void event_interrupt_wq_v9(struct kfd_node *dev,
 		if (vmid_type && client_id == SOC15_IH_CLIENTID_VMC)
 			hub_inst = node_id / 4;
 
-		if (amdgpu_amdkfd_ras_query_utcl2_poison_status(dev->adev,
-					hub_inst, vmid_type)) {
+		if (source_id == SOC15_INTSRC_VMC_UTCL2_POISON) {
 			event_interrupt_poison_consumption_v9(dev, pasid, client_id);
 			return;
 		}
diff --git a/drivers/gpu/drm/amd/amdkfd/soc15_int.h b/drivers/gpu/drm/amd/amdkfd/soc15_int.h
index 10138676f27f..e5c0205f2618 100644
--- a/drivers/gpu/drm/amd/amdkfd/soc15_int.h
+++ b/drivers/gpu/drm/amd/amdkfd/soc15_int.h
@@ -29,6 +29,7 @@
 #define SOC15_INTSRC_CP_BAD_OPCODE	183
 #define SOC15_INTSRC_SQ_INTERRUPT_MSG	239
 #define SOC15_INTSRC_VMC_FAULT		0
+#define SOC15_INTSRC_VMC_UTCL2_POISON	1
 #define SOC15_INTSRC_SDMA_TRAP		224
 #define SOC15_INTSRC_SDMA_ECC		220
 #define SOC21_INTSRC_SDMA_TRAP		49
-- 
2.17.1



More information about the amd-gfx mailing list