[Nouveau] [PATCH 9/9] perf: change pcie speed on pstate change

[Roy Spliet]

Comment in-line.
Cheers,

Roy

Op 12-10-15 om 21:27 schreef Karol Herbst:
> Signed-off-by: Karol Herbst <nouveau at karolherbst.de>
> ---
>   drm/nouveau/nvkm/subdev/clk/base.c | 7 +++++++
>   1 file changed, 7 insertions(+)
>
> diff --git a/drm/nouveau/nvkm/subdev/clk/base.c b/drm/nouveau/nvkm/subdev/clk/base.c
> index 7ae4f26..4e5122b 100644
> --- a/drm/nouveau/nvkm/subdev/clk/base.c
> +++ b/drm/nouveau/nvkm/subdev/clk/base.c
> @@ -176,6 +176,7 @@ nvkm_pstate_prog(struct nvkm_clk *clk, int pstatei)
>   {
>   	struct nvkm_subdev *subdev = &clk->subdev;
>   	struct nvkm_ram *ram = subdev->device->fb->ram;
> +	struct nvkm_pci *pci = subdev->device->pci;
>   	struct nvkm_pstate *pstate;
>   	int ret, idx = 0;
>   
> @@ -187,6 +188,12 @@ nvkm_pstate_prog(struct nvkm_clk *clk, int pstatei)
>   	nvkm_debug(subdev, "setting performance state %d\n", pstatei);
>   	clk->pstate = pstatei;
>   
> +	if (pci) {
> +		ret = nvkm_pci_set_pcie_link(pci, pstate->pcie_speed, pstate->pcie_width);
> +		if (ret < 0)
> +			nvkm_error(subdev, "failed changing pcie speed with: %i\n", ret);
Is this an error? It makes it sound like a serious issue, even though 
this is expected behaviour eg. when the motherboard doesn't support the 
desired PCIe speed. Maybe a "debug" message is more appropriate here.
> +	}
> +
>   	if (ram && ram->func->calc) {
>   		int khz = pstate->base.domain[nv_clk_src_mem];
>   		do {