Re: [PATCH v4 2/2] arm64: dts: mt8192: Add vcodec lat and core nodes

[Nícolas F. R. A. Prado]

On Mon, Nov 21, 2022 at 12:30:37PM +0000, Allen-KH Cheng (程冠勳) wrote:
> Hi Nícolas,
> 
> On Fri, 2022-11-18 at 09:10 -0500, Nícolas F. R. A. Prado wrote:
> > On Fri, Sep 30, 2022 at 07:22:37PM +0800, Allen-KH Cheng wrote:
> > > Add vcodec lat and core nodes for mt8192 SoC.
> > > 
> > > Signed-off-by: Allen-KH Cheng <allen-kh.cheng@xxxxxxxxxxxx>
> > > Tested-by: Chen-Yu Tsai <wenst@xxxxxxxxxxxx>
> > > Reviewed-by: AngeloGioacchino Del Regno <
> > > angelogioacchino.delregno@xxxxxxxxxxxxx>
> > > ---
> > >  arch/arm64/boot/dts/mediatek/mt8192.dtsi | 60
> > > ++++++++++++++++++++++++
> > >  1 file changed, 60 insertions(+)
> > > 
> > > diff --git a/arch/arm64/boot/dts/mediatek/mt8192.dtsi
> > > b/arch/arm64/boot/dts/mediatek/mt8192.dtsi
> > > index 6b20376191a7..92a20f87468b 100644
> > > --- a/arch/arm64/boot/dts/mediatek/mt8192.dtsi
> > > +++ b/arch/arm64/boot/dts/mediatek/mt8192.dtsi
> > > @@ -1449,6 +1449,66 @@
> > >  			power-domains = <&spm
> > > MT8192_POWER_DOMAIN_ISP2>;
> > >  		};
> > >  
> > > +		vcodec_dec: video-codec@16000000 {
> > > +			compatible = "mediatek,mt8192-vcodec-dec";
> > > +			reg = <0 0x16000000 0 0x1000>;
> > > +			mediatek,scp = <&scp>;
> > > +			iommus = <&iommu0 M4U_PORT_L4_VDEC_MC_EXT>;
> > > +			dma-ranges = <0x1 0x0 0x0 0x40000000 0x0
> > > 0xfff00000>;
> > 
> > Hi,
> > 
> > since commit 951d48855d86 ("of: Make of_dma_get_range() work on bus
> > nodes") [1]
> > was merged this no longer works as is. Running the fluster codec
> > tests results
> > in IOMMU faults:
> > 
> > 	[  386.233976] mtk-iommu 1401d000.m4u: fault type=0x280
> > iova=0x1fcdc0000 pa=0x0 master=0x500041c(larb=4 port=7) layer=0 read
> > 	[  386.250666] mtk_vdec_worker(),241:
> > [MTK_V4L2][ERROR]  <===[138], src_buf[0] sz=0x298 pts=0
> > vdec_if_decode() ret=1 res_chg=0===>
> > 
> > The issue is that the DMA configuration supplied by dma-ranges is now
> > looked for
> > in the parent node, so the vcodec_dec node no longer gets the
> > configuration it
> > expected.
> > 
> > That said, given that the node already uses the IOMMU for the address
> > translations (iommus property), there shouldn't even be a dma-ranges
> > property.
> > Indeed simply removing the dma-ranges property from this node fixes
> > the issue
> > and gets the decoder working again.
> > 
> > Thanks,
> > Nícolas
> > 
> > [1] 
> > https://urldefense.com/v3/__https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=f1ad5338a4d57fe1fe6475003acb8c70bf9d1bdf__;!!CTRNKA9wMg0ARbw!xdhhnvXMY5-BjI2BXPHQI-Hw8zgtZ1lvFyFFv7KtNuCDxW17VC7RqAaW9B_uXsQucT1sLk_DUl-c99ijF9dF8QXbJQ$
> >  
> 
> Noted!
> 
> The paret node should be
> 
> vcodec_dec: video-codec@16000000 {
> 	compatible = "mediatek,mt8192-vcodec-dec";
> 	reg = <0 0x16000000 0 0x1000>;
> 	mediatek,scp = <&scp>;
> 	iommus = <&iommu0 M4U_PORT_L4_VDEC_MC_EXT>;
> 	#address-cells = <2>;
> 	#size-cells = <2>;
> 	ranges = <0 0 0 0x16000000 0 0x26000>;
> 	
> 	video-codec-lat@10000 {
> ...
> 
> }
> 
> Am I right?

Yes, that's right.

Thanks,
Nícolas