mbox series

[0/3] media: rockchip: Add rkvdec2 driver

Message ID 20240615015734.1612108-1-detlev.casanova@collabora.com
Headers show
Series media: rockchip: Add rkvdec2 driver | expand

Message

Detlev Casanova June 15, 2024, 1:56 a.m. UTC
Add a rkvdec2 driver for newer video decoder found on rk3588 based SoC.

See the first commit message for implementation details.

Detlev Casanova (3):
  media: rockchip: Introduce the rkvdec2 driver
  media: dt-bindings: rockchip: Document RK3588 Video Decoder 2 bindings
  arm64: dts: rockchip: Add rkvdec2 Video Decoder on rk3588(s)

 .../bindings/media/rockchip,vdec2.yaml        |   80 ++
 .../boot/dts/rockchip/rk3588-rock-5b.dts      |    4 +
 .../boot/dts/rockchip/rk3588s-orangepi-5.dts  |    4 +
 arch/arm64/boot/dts/rockchip/rk3588s.dtsi     |   19 +
 drivers/staging/media/Kconfig                 |    1 +
 drivers/staging/media/Makefile                |    1 +
 drivers/staging/media/rkvdec2/Kconfig         |   15 +
 drivers/staging/media/rkvdec2/Makefile        |    3 +
 drivers/staging/media/rkvdec2/TODO            |   13 +
 drivers/staging/media/rkvdec2/rkvdec2-h264.c  |  899 +++++++++++++
 drivers/staging/media/rkvdec2/rkvdec2-regs.h  |  372 ++++++
 drivers/staging/media/rkvdec2/rkvdec2.c       | 1160 +++++++++++++++++
 drivers/staging/media/rkvdec2/rkvdec2.h       |  123 ++
 13 files changed, 2694 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/media/rockchip,vdec2.yaml
 create mode 100644 drivers/staging/media/rkvdec2/Kconfig
 create mode 100644 drivers/staging/media/rkvdec2/Makefile
 create mode 100644 drivers/staging/media/rkvdec2/TODO
 create mode 100644 drivers/staging/media/rkvdec2/rkvdec2-h264.c
 create mode 100644 drivers/staging/media/rkvdec2/rkvdec2-regs.h
 create mode 100644 drivers/staging/media/rkvdec2/rkvdec2.c
 create mode 100644 drivers/staging/media/rkvdec2/rkvdec2.h

Comments

Nicolas Dufresne June 17, 2024, 1:52 p.m. UTC | #1
Hi,

Le dimanche 16 juin 2024 à 10:40 +0200, Diederik de Haas a écrit :
> On Saturday, 15 June 2024 21:44:32 CEST Detlev Casanova wrote:
> > > So is this just an (unfortunate) use of the same words or is that wiki
> > > page just wrong ... or better yet: does rkvdec2 support RK356x too?
> > 
> > Yes, the vdpu34x decoder on rk356x socs should be supported by this driver
> > but I don't have boards to test that unfortunately.
> > 
> > This might also be used on future rockchip releases like the rk3576. But
> > they all have their own adaptations. If you can test it on rk3568 based
> > hardware, I'll happily add a compatible for it.
> 
> It would be great if you'd add a compatible for it.
> I don't have rk3568 based HW, but I do have rk3566 based HW and AFAIK those 
> are the same when it comes to the 'video' stuff.

Our usual approach is to require at least a "Test-by:" to include patches
written without HW. I think it will come soon enough, and we can focus on
getting the driver in at this moment.

Nicolas
Detlev Casanova June 17, 2024, 2:31 p.m. UTC | #2
On Sunday, June 16, 2024 3:28:25 A.M. EDT Heiko Stuebner wrote:
> Am Samstag, 15. Juni 2024, 21:55:54 CEST schrieb Detlev Casanova:
> > On Saturday, June 15, 2024 4:25:27 A.M. EDT Jonas Karlman wrote:
> > > Hi Detlev,
> > > 
> > > On 2024-06-15 03:56, Detlev Casanova wrote:
> > > > Add the rkvdec2 Video Decoder to the RK3588s devicetree.
> > > > 
> > > > Signed-off-by: Detlev Casanova <detlev.casanova@collabora.com>
> > > > ---
> > > > 
> > > >  .../boot/dts/rockchip/rk3588-rock-5b.dts      |  4 ++++
> > > >  .../boot/dts/rockchip/rk3588s-orangepi-5.dts  |  4 ++++
> > > >  arch/arm64/boot/dts/rockchip/rk3588s.dtsi     | 19
> > > >  +++++++++++++++++++
> > > >  3 files changed, 27 insertions(+)
> > > > 
> > > > diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
> > > > b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts index
> > > > c551b676860c..965322c24a65 100644
> > > > --- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
> > > > +++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
> > > > @@ -503,6 +503,10 @@ &pwm1 {
> > > > 
> > > >  	status = "okay";
> > > >  
> > > >  };
> > > > 
> > > > +&rkvdec0 {
> > > > +	status = "okay";
> > > > +};
> > > 
> > > Enable of rkvdec0 should probably be split out from the patch that adds
> > > the rkvdec0 node to soc dtsi.
> > 
> > Ack
> > 
> > > Also why is rkvdec0 only enabled on rock-5b and orangepi-5?
> > 
> > I only could test on those two but I can enable it on all rk3588 devices.
> > 
> > > > +
> > > > 
> > > >  &saradc {
> > > >  
> > > >  	vref-supply = <&avcc_1v8_s0>;
> > > >  	status = "okay";
> > > > 
> > > > diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts
> > > > b/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts index
> > > > feea6b20a6bf..2828fb4c182a 100644
> > > > --- a/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts
> > > > +++ b/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts
> > > > @@ -321,6 +321,10 @@ typec5v_pwren: typec5v-pwren {
> > > > 
> > > >  	};
> > > >  
> > > >  };
> > > > 
> > > > +&rkvdec0 {
> > > > +	status = "okay";
> > > > +};
> > > > +
> > > > 
> > > >  &saradc {
> > > >  
> > > >  	vref-supply = <&avcc_1v8_s0>;
> > > >  	status = "okay";
> > > > 
> > > > diff --git a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi
> > > > b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi index
> > > > 0fecbf46e127..09672636dcea 100644
> > > > --- a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi
> > > > +++ b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi
> > > > @@ -3034,6 +3034,9 @@ system_sram2: sram@ff001000 {
> > > > 
> > > >  		ranges = <0x0 0x0 0xff001000 0xef000>;
> > > >  		#address-cells = <1>;
> > > >  		#size-cells = <1>;
> > > 
> > > Blank line is missing.
> > > 
> > > > +		rkvdec0_sram: rkvdec-sram@0 {
> > > > +			reg = <0x0 0x78000>;
> > > > +		};
> > > > 
> > > >  	};
> > > >  	
> > > >  	pinctrl: pinctrl {
> > > > 
> > > > @@ -3103,6 +3106,22 @@ gpio4: gpio@fec50000 {
> > > > 
> > > >  			#interrupt-cells = <2>;
> > > >  		
> > > >  		};
> > > >  	
> > > >  	};
> > > > 
> > > > +
> > > > +	rkvdec0: video-decoder@fdc38100 {
> > > > +		compatible = "rockchip,rk3588-vdec2";
> > > > +		reg = <0x0 0xfdc38100 0x0 0x500>;
> > > > +		interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH 0>;
> > > > +		clocks = <&cru ACLK_RKVDEC0>, <&cru HCLK_RKVDEC0>,
> > 
> > <&cru
> > 
> > > > CLK_RKVDEC0_CORE>, +			 <&cru
> > 
> > CLK_RKVDEC0_CA>, <&cru
> > 
> > > > CLK_RKVDEC0_HEVC_CA>;
> > > > +		clock-names = "axi", "ahb", "core",
> > > > +			      "cabac", "hevc_cabac";
> > > > +		assigned-clocks = <&cru ACLK_RKVDEC0>, <&cru
> > 
> > CLK_RKVDEC0_CORE>,
> > 
> > > > +				  <&cru CLK_RKVDEC0_CA>, <&cru
> > 
> > CLK_RKVDEC0_HEVC_CA>;
> > 
> > > > +		assigned-clock-rates = <800000000>, <600000000>,
> > > > +				       <600000000>, 
<1000000000>;
> > > > +		power-domains = <&power RK3588_PD_RKVDEC0>;
> > > 
> > > iommus and resets should probably be added.
> > > 
> > > > +		status = "disabled";
> > > > +	};
> > > 
> > > The iommu node for rkvdec0_mmu seem to be missing, is it not required to
> > > be able to use memory >4GiB as decoding buffers?
> > 
> > I need to check if the current rockchip iommu driver will work for this
> > decoder. I remember that the iommu code for AV1 was a bit different, not
> > sure about this rkvdec.
> > 
> > > I would also consider adding the rkvdec1 node(s), if I am understanding
> > > correctly they can both be used in a cluster or completely independent.
> > 
> > They can be used independently, yes. I'll add rkvdec1 for rk3588 devices
> > (rk3588s only has  1 core)
> 
> Please check in with Sebastian Reichel about clusters/independent
> controllers. He had a lot of fruitful discussions for the VEPU121/VPU121
> support he is working on.

Yes, basically, it makes the driver check for all nodes with the same 
compatible and list the instances in the same device instance.
If multicore is not supported, the other instances can simple be ignored.

See here: https://lore.kernel.org/linux-kernel/20240613135034.31684-4-sebastian.reichel@collabora.com/

> Baseline being, while we want the hw to be described correctly wrt the
> multiple instances, we don't generally want to expose them individually
> to userspace, because that would then require userspace to do all the
> scheduling.

Yes, so Sebastien's patch will allow the device tree to have the 2 cores but 
only one visible by the userspace (even when multicore decoding is not 
supported)