[PATCH v3 02/10] arm64: dts: rockchip: Add nodes for NPU and its MMU to rk3588s

[Tomeu Vizoso]

On Mon, May 19, 2025 at 10:47 AM Krzysztof Kozlowski <krzk at kernel.org> wrote:
>
> On 19/05/2025 10:27, Tomeu Vizoso wrote:
> > On Mon, May 19, 2025 at 8:08 AM Krzysztof Kozlowski <krzk at kernel.org> wrote:
> >>
> >> On 16/05/2025 18:53, Tomeu Vizoso wrote:
> >>> See Chapter 36 "RKNN" from the RK3588 TRM (Part 1).
> >>>
> >>> This is a derivative of NVIDIA's NVDLA, but with its own front-end
> >>> processor.
> >>>
> >>> The IP is divided in three cores, programmed independently. The first
> >>> core though is special, requiring to be powered on before any of the
> >>> others can be used.
> >>>
> >>> The IOMMU of the first core is also special in that it has two subunits
> >>> (read/write?) that need to be programmed in sync.
> >>>
> >>> v2:
> >>> - Have one device for each NPU core (Sebastian Reichel)
> >>> - Have one device for each IOMMU (Sebastian Reichel)
> >>> - Correctly sort nodes (Diederik de Haas)
> >>> - Add rockchip,iommu compatible to IOMMU nodes (Sebastian Reichel)
> >>>
> >>> v3:
> >>> - Adapt to a split of the register block in the DT bindings (Nicolas
> >>>   Frattaroli)
> >>>
> >>> Signed-off-by: Tomeu Vizoso <tomeu at tomeuvizoso.net>
> >>> ---
> >>>  arch/arm64/boot/dts/rockchip/rk3588-base.dtsi | 85 +++++++++++++++++++++++++++
> >>>  1 file changed, 85 insertions(+)
> >>>
> >>> diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
> >>> index 1e18ad93ba0ebdad31642b88ff0f90ef4e8dc76f..7b961ab838212fad8e4a70390fdc917a828433a9 100644
> >>> --- a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
> >>> +++ b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
> >>> @@ -1136,6 +1136,91 @@ power-domain at RK3588_PD_SDMMC {
> >>>               };
> >>>       };
> >>>
> >>> +     rknn_core_top: npu-core at fdab0000 {
> >>
> >> npu@
> >>
> >>> +             compatible = "rockchip,rk3588-rknn-core-top", "rockchip,rknn-core-top";
> >>
> >> You never tested this. Test before sending instead of relying on us or
> >> after merging.
> >
> > Can you please extend on this? I have tested this series before
> > sending and I don't understand what you mean here.
>
> I mean exactly that: it was not tested, because warnings are clearly
> visible/expected. I also found now Rob's report which even shows you the
> warnings, so how come you still claim this was tested?

Ah yes, I'm working on those warnings. I understood you as saying that
the code hadn't been run and tested that it works correctly (I do have
a test suite that I run as part of my testing).

Regards,

Tomeu