From 086809c82c96116aed78f762e4f1d61a4e0210a7 Mon Sep 17 00:00:00 2001 From: Ellen Pan Date: Tue, 29 Apr 2025 17:18:44 -0400 Subject: drm/amdgpu: Implement unrecoverable error message handling for VFs This notification may arrive in VF mailbox while polling for response from another event. This patches covers the following scenarios: - If VF is already in RMA state, then do not attempt to contact the host. Host will ignore the VF after sending the notification. - If the notification is detected during polling, then set the RMA status, and return error to caller. - If the notification arrives by interrupt, then set the RMA status and queue a reset. This reset will fail and VF will stop runtime services. Reviewed-by: Shravan Kumar Gande Signed-off-by: Victor Skvortsov Signed-off-by: Ellen Pan Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_device.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index ccc6217761bf..a2997ededd0e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -6150,6 +6150,11 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */ /* Actual ASIC resets if needed.*/ /* Host driver will handle XGMI hive reset for SRIOV */ if (amdgpu_sriov_vf(adev)) { + + /* Bail out of reset early */ + if (amdgpu_ras_is_rma(adev)) + return -ENODEV; + if (amdgpu_ras_get_fed_status(adev) || amdgpu_virt_rcvd_ras_interrupt(adev)) { dev_dbg(adev->dev, "Detected RAS error, wait for FLR completion\n"); amdgpu_ras_set_fed(adev, true); -- cgit v1.2.3