From 1b6ef74b2b03b54776778476f8adf87dd4f8beb1 Mon Sep 17 00:00:00 2001 From: Lijo Lazar Date: Thu, 22 Feb 2024 14:16:57 +0530 Subject: drm/amdgpu: Add fatal error detected flag For a RAS error that needs a full reset to recover, set the fatal error status. Clear the status once the device is reset. Signed-off-by: Lijo Lazar Reviewed-by: Asad Kamal Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h index d10e5bb0e52f..e0f8ce9d8440 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h @@ -477,6 +477,8 @@ struct amdgpu_ras { wait_queue_head_t page_retirement_wq; struct mutex page_retirement_lock; atomic_t page_retirement_req_cnt; + /* Fatal error detected flag */ + atomic_t fed; }; struct ras_fs_data { @@ -873,4 +875,8 @@ void amdgpu_ras_add_mca_err_addr(struct ras_err_info *err_info, void amdgpu_ras_del_mca_err_addr(struct ras_err_info *err_info, struct ras_err_addr *mca_err_addr); + +void amdgpu_ras_set_fed(struct amdgpu_device *adev, bool status); +bool amdgpu_ras_get_fed_status(struct amdgpu_device *adev); + #endif -- cgit v1.2.3