drm/amdgpu/virt: skip VM fault handler for VF

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.

Signed-off-by: Pixel Ding <Pixel.Ding@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 7669b3259f35e23dab22352b5deb3ffdf4631491..65025080a4b883ba80c855513d540807d72194b1 100644 (file)
--- 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);