6.10-stable review patch. If anyone has any objections, please let me know.
------------------
From: Tao Zhou tao.zhou1@amd.com
[ Upstream commit 09a3d8202df1e9fa1eb5f5f63524c8948275ff4c ]
Indicate fatal error for each RAS block and NBIO.
Signed-off-by: Tao Zhou tao.zhou1@amd.com Reviewed-by: Hawking Zhang Hawking.Zhang@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 1 + drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c | 1 + 2 files changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 57fdc4ab9c54..7ba90c5974ed 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -2112,6 +2112,7 @@ static void amdgpu_ras_interrupt_umc_handler(struct ras_manager *obj, /* Let IP handle its data, maybe we need get the output * from the callback to update the error type/count, etc */ + amdgpu_ras_set_fed(obj->adev, true); ret = data->cb(obj->adev, &err_data, entry); /* ue will trigger an interrupt, and in that case * we need do a reset to recovery the whole system. diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index 750ce281b97b..e326d6f06ca9 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -418,6 +418,7 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device /* ras_controller_int is dedicated for nbif ras error, * not the global interrupt for sync flood */ + amdgpu_ras_set_fed(adev, true); amdgpu_ras_reset_gpu(adev); }