VF uses KIQ to access registers. When VM fault occurs, the driver
can't get back the fence of KIQ submission and runs into CPU soft
lockup.
v2: print IV entry info
Signed-off-by: Pixel Ding <Pixel.Ding at amd.com>
---
drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 7669b32..6502508 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -1237,6 +1237,13 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
{
u32 addr, status, mc_client;
+ if (amdgpu_sriov_vf(adev)) {
+ dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
+ entry->src_id, entry->src_data);
+ dev_err(adev->dev, " Can't decode VM fault info here on SRIOV VF\n");
+ return 0;
+ }
+
addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR);
status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS);
mc_client = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_MCCLIENT);
--
2.7.4
