From ab66c832847fcdffc97d4591ba5547e3990d9d33 Mon Sep 17 00:00:00 2001 From: Zhigang Luo Date: Thu, 29 Feb 2024 16:04:35 -0500 Subject: drm/amdgpu: trigger flr_work if reading pf2vf data failed if reading pf2vf data failed 30 times continuously, it means something is wrong. Need to trigger flr_work to recover the issue. also use dev_err to print the error message to get which device has issue and add warning message if waiting IDH_FLR_NOTIFICATION_CMPL timeout. Signed-off-by: Zhigang Luo Acked-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (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 efb3b7e74b80..3204b8f6edeb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -143,6 +143,8 @@ const char *amdgpu_asic_name[] = { "LAST", }; +static inline void amdgpu_device_stop_pending_resets(struct amdgpu_device *adev); + /** * DOC: pcie_replay_count * @@ -4968,6 +4970,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, retry: amdgpu_amdkfd_pre_reset(adev); + amdgpu_device_stop_pending_resets(adev); + if (from_hypervisor) r = amdgpu_virt_request_full_gpu(adev, true); else @@ -5708,11 +5712,12 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */ tmp_adev->asic_reset_res = r; } - /* - * Drop all pending non scheduler resets. Scheduler resets - * were already dropped during drm_sched_stop - */ - amdgpu_device_stop_pending_resets(tmp_adev); + if (!amdgpu_sriov_vf(tmp_adev)) + /* + * Drop all pending non scheduler resets. Scheduler resets + * were already dropped during drm_sched_stop + */ + amdgpu_device_stop_pending_resets(tmp_adev); } /* Actual ASIC resets if needed.*/ -- cgit