[PATCH v2 00/10] R-Car DU: LVDS dual-link mode support

[PATCH v2 00/10] R-Car DU: LVDS dual-link mode support

[Laurent Pinchart]

Hello everybody,

This patch series implements support for LVDS dual-link mode in the
R-Car DU and R-Car LVDS encoder drivers, and well as in the thc63lvd1024
LVDS decoder driver.

LVDS dual-link is a mode of operation where two individual LVDS links
are operated together to carry even- and odd-numbered pixels separately.
This doubles the possible bandwidth of the video transmission. Both the
transmitter and the receiver need to support this mode of operation.

The R-Car D3 and E3 SoCs include two independent LVDS encoders that can
be grouped together to operate in dual-link mode. When used separately,
the LVDS encoders are connected to two different CRTCs and transmit
independent video streams. When used in dual-link mode, the first LVDS
encoder is connected to the first CRTC, and split even- and odd-numbered
pixels. It transmits half of the pixels on its LVDS output, and sends
the other half to the second LVDS encoder for transmittion over the
second LVDS link. The second LVDS encoder thus operates under control of
the first one, and isn't connected directly to a CRTC.

On the receiving side, the THC63LVD1024 LVDS-to-parallel bridge has two
LVDS inputs and two parallel outputs. It can operate in four different
modes:

- Single-in, single-out: The first LVDS input receives the video stream,
  and the bridge outputs it on the first parallel output. The second
  LVDS input and the second parallel output are not used.

- Single-in, dual-out: The first LVDS input receives the video stream,
  and the bridge splits even- and odd-numbered pixels and outputs them
  on the first and second parallel outputs. The second LVDS input is not
  used.

- Dual-in, single-out: The two LVDS inputs are used in dual-link mode,
  and the bridge combines the even- and odd-numbered pixels and outputs
  them on the first parallel output. The second parallel output is not
  used.

- Dual-in, dual-out: The two LVDS inputs are used in dual-link mode,
  and the bridge outputs the even- and odd-numbered pixels on the first
  parallel output.

The operating mode is selected by two input pins of the bridge, which
are connected to DIP switches on the development boards I use. The mode
is thus fixed from a Linux point of view.

Patch 01/10 adds a new dual_link boolen field to the drm_bridge_timings
structure to let bridges report their LVDS mode of operation. Patch
02/10 clarifies the THC63LVD1024 DT bindings to document dual-link
operation, and patch 03/10 implements dual-link support in the
thc64lvd1024 bridge driver by setting the drm_bridge_timings dual_link
field according to the mode selected through DT.

Patch 04/10 extends the R-Car LVDS DT bindings to specify the companion
LVDS encoder for dual-link operation. Patches 05/10 then performs a
small cleanup in the LVDS encoder driver. Patch 06/10 implements
dual-link support in the LVDS encoder driver, which involves retrieving
the operation mode from the LVDS receiver, locating the companion LVDS
encoder, and configuring both encoders when dual-link operation is
desired. The API towards the DU driver is also extended to report the
mode of operation.

Patch 07/10 implements dual-link mode support in the DU driver. There is
no specific configuration to be performed there, as dual-link is fully
implemented in the LVDS encoder driver, but the DU driver has to skip
creation of the DRM encoder and connector related to the second LVDS
encoder when dual-link is used, as the second LVDS encoder operates as a
slave of the first one, transparently from a CRTC (and thus userspace)
perspective.

Patch 08/10 specifies the companion LVDS encoder in the D3 and E3 DT
bindings. This by itself doesn't enable dual-link mode, the LVDS0
encoder is still connected to the HDMI output through LVDS receiver, and
the LVDS1 encoder is not used. Patches 09/10 and 10/10, not intended to
be merged, enable dual-link operation for the D3 and E3 boards for
testing and require flipping DIP switches on the boards.

The patches are based on top of my drm/du/next branch, and are available
for convenience at

        git://linuxtv.org/pinchartl/media.git drm/du/lvds/dual-link

They have been tested successfully on the D3 Draak board. I expect them
to work on E3 as well, but I don't have access to an Ebisu board to test
this.

Laurent Pinchart (10):
  drm: bridge: Add dual_link field to the drm_bridge_timings structure
  dt-bindings: display: bridge: thc63lvd1024: Document dual-link
    operation
  drm: bridge: thc63: Report input bus mode through bridge timings
  dt-bindings: display: renesas: lvds: Add renesas,companion property
  drm: rcar-du: lvds: Remove LVDS double-enable checks
  drm: rcar-du: lvds: Add support for dual-link mode
  drm: rcar-du: Skip LVDS1 output on Gen3 when using dual-link LVDS mode
  arm64: dts: renesas: r8a7799[05]: Point LVDS0 to its companion LVDS1
  [HACK] arm64: dts: renesas: draak: Enable LVDS dual-link operation
  [HACK] arm64: dts: renesas: ebisu: Enable LVDS dual-link operation

 .../bindings/display/bridge/renesas,lvds.txt  |   6 +
 .../display/bridge/thine,thc63lvd1024.txt     |   6 +
 .../arm64/boot/dts/renesas/r8a77990-ebisu.dts |  21 ++-
 arch/arm64/boot/dts/renesas/r8a77990.dtsi     |   2 +
 .../arm64/boot/dts/renesas/r8a77995-draak.dts |  21 ++-
 arch/arm64/boot/dts/renesas/r8a77995.dtsi     |   2 +
 drivers/gpu/drm/bridge/thc63lvd1024.c         |  54 ++++++--
 drivers/gpu/drm/rcar-du/rcar_du_encoder.c     |  12 ++
 drivers/gpu/drm/rcar-du/rcar_du_kms.c         |   2 +-
 drivers/gpu/drm/rcar-du/rcar_lvds.c           | 123 +++++++++++++-----
 drivers/gpu/drm/rcar-du/rcar_lvds.h           |   5 +
 include/drm/drm_bridge.h                      |   8 ++
 12 files changed, 214 insertions(+), 48 deletions(-)

-- 
Regards,

Laurent Pinchart

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 02/10] dt-bindings: display: bridge: thc63lvd1024: Document dual-link operation

[Laurent Pinchart]

The THC63LVD1024 LVDS decoder can operate in two modes, single-link or
dual-link. In dual-link mode both input ports are used to carry even-
and odd-numbered pixels separately. Document this in the DT bindings,
along with the related rules governing port and usage.

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Reviewed-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
---
 .../bindings/display/bridge/thine,thc63lvd1024.txt          | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt b/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt
index 37f0c04d5a28..d17d1e5820d7 100644
--- a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt
+++ b/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt
@@ -28,6 +28,12 @@ Optional video port nodes:
 - port@1: Second LVDS input port
 - port@3: Second digital CMOS/TTL parallel output
 
+The device can operate in single-link mode or dual-link mode. In single-link
+mode, all pixels are received on port@0, and port@1 shall not contain any
+endpoint. In dual-link mode, even-numbered pixels are received on port@0 and
+odd-numbered pixels on port@1, and both port@0 and port@1 shall contain
+endpoints.
+
 Example:
 --------
 
-- 
Regards,

Laurent Pinchart

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 04/10] dt-bindings: display: renesas: lvds: Add renesas, companion property

[Laurent Pinchart]

Add a new optional renesas,companion property to point to the companion
LVDS encoder. This is used to support dual-link operation where the main
LVDS encoder splits even-numbered and odd-numbered pixels between the
two LVDS encoders.

The new property doesn't control the mode of operation, it only
describes the relationship between the master and companion LVDS
encoders.

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
---
Changes since v1:

- Fixed typo
---
 .../devicetree/bindings/display/bridge/renesas,lvds.txt     | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt b/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt
index 900a884ad9f5..f2cc01d54cbd 100644
--- a/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt
+++ b/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt
@@ -45,6 +45,12 @@ OF graph bindings specified in Documentation/devicetree/bindings/graph.txt.
 
 Each port shall have a single endpoint.
 
+Optional properties:
+
+- renesas,companion : phandle to the companion LVDS encoder. This property is
+  valid for the first LVDS encoder on D3 and E3 SoCs only, and points to the
+  second encoder to be used as a companion in dual-link mode.
+
 
 Example:
 
-- 
Regards,

Laurent Pinchart

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 00/10] R-Car DU: LVDS dual-link mode support

[Geert Uytterhoeven]

Hi Laurent,

On Sat, May 11, 2019 at 11:07 PM Laurent Pinchart
<laurent.pinchart+renesas@ideasonboard.com> wrote:
> On the receiving side, the THC63LVD1024 LVDS-to-parallel bridge has two
> LVDS inputs and two parallel outputs. It can operate in four different
> modes:
>
> - Single-in, single-out: The first LVDS input receives the video stream,
>   and the bridge outputs it on the first parallel output. The second
>   LVDS input and the second parallel output are not used.
>
> - Single-in, dual-out: The first LVDS input receives the video stream,
>   and the bridge splits even- and odd-numbered pixels and outputs them
>   on the first and second parallel outputs. The second LVDS input is not
>   used.
>
> - Dual-in, single-out: The two LVDS inputs are used in dual-link mode,
>   and the bridge combines the even- and odd-numbered pixels and outputs
>   them on the first parallel output. The second parallel output is not
>   used.
>
> - Dual-in, dual-out: The two LVDS inputs are used in dual-link mode,
>   and the bridge outputs the even- and odd-numbered pixels on the first
>   parallel output.

and the second?

> The operating mode is selected by two input pins of the bridge, which
> are connected to DIP switches on the development boards I use. The mode
> is thus fixed from a Linux point of view.

Can the state of these switches be read from software?

Gr{oetje,eeting}s,

                        Geert

--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 02/10] dt-bindings: display: bridge: thc63lvd1024: Document dual-link operation

[Geert Uytterhoeven]

Hi Laurent,

On Sat, May 11, 2019 at 11:07 PM Laurent Pinchart
<laurent.pinchart+renesas@ideasonboard.com> wrote:
> The THC63LVD1024 LVDS decoder can operate in two modes, single-link or
> dual-link. In dual-link mode both input ports are used to carry even-
> and odd-numbered pixels separately. Document this in the DT bindings,
> along with the related rules governing port and usage.
>
> Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
> Reviewed-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
> ---
>  .../bindings/display/bridge/thine,thc63lvd1024.txt          | 6 ++++++
>  1 file changed, 6 insertions(+)
>
> diff --git a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt b/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt
> index 37f0c04d5a28..d17d1e5820d7 100644
> --- a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt
> +++ b/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt
> @@ -28,6 +28,12 @@ Optional video port nodes:
>  - port@1: Second LVDS input port
>  - port@3: Second digital CMOS/TTL parallel output
>
> +The device can operate in single-link mode or dual-link mode. In single-link
> +mode, all pixels are received on port@0, and port@1 shall not contain any
> +endpoint. In dual-link mode, even-numbered pixels are received on port@0 and
> +odd-numbered pixels on port@1, and both port@0 and port@1 shall contain
> +endpoints.

This describes single/dual input.
Does single/dual output need to be described, too?

BTW, I see the second input/output set is optional, wile the first set
is required.  Could it happen the hardware is wired for the second
set only?

Gr{oetje,eeting}s,

                        Geert

-- 
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 00/10] R-Car DU: LVDS dual-link mode support

[Laurent Pinchart]

Hi Geert,

On Sun, May 12, 2019 at 10:55:20AM +0200, Geert Uytterhoeven wrote:
> On Sat, May 11, 2019 at 11:07 PM Laurent Pinchart wrote:
> > On the receiving side, the THC63LVD1024 LVDS-to-parallel bridge has two
> > LVDS inputs and two parallel outputs. It can operate in four different
> > modes:
> >
> > - Single-in, single-out: The first LVDS input receives the video stream,
> >   and the bridge outputs it on the first parallel output. The second
> >   LVDS input and the second parallel output are not used.
> >
> > - Single-in, dual-out: The first LVDS input receives the video stream,
> >   and the bridge splits even- and odd-numbered pixels and outputs them
> >   on the first and second parallel outputs. The second LVDS input is not
> >   used.
> >
> > - Dual-in, single-out: The two LVDS inputs are used in dual-link mode,
> >   and the bridge combines the even- and odd-numbered pixels and outputs
> >   them on the first parallel output. The second parallel output is not
> >   used.
> >
> > - Dual-in, dual-out: The two LVDS inputs are used in dual-link mode,
> >   and the bridge outputs the even- and odd-numbered pixels on the first
> >   parallel output.
> 
> and the second?

I should have read "on the first and second parallel outputs
respectively" indeed.

> > The operating mode is selected by two input pins of the bridge, which
> > are connected to DIP switches on the development boards I use. The mode
> > is thus fixed from a Linux point of view.
> 
> Can the state of these switches be read from software?

Unfortunately not :-(

-- 
Regards,

Laurent Pinchart
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 02/10] dt-bindings: display: bridge: thc63lvd1024: Document dual-link operation

[Laurent Pinchart]

Hi Geert,

On Sun, May 12, 2019 at 10:58:54AM +0200, Geert Uytterhoeven wrote:
> On Sat, May 11, 2019 at 11:07 PM Laurent Pinchart wrote:
> > The THC63LVD1024 LVDS decoder can operate in two modes, single-link or
> > dual-link. In dual-link mode both input ports are used to carry even-
> > and odd-numbered pixels separately. Document this in the DT bindings,
> > along with the related rules governing port and usage.
> >
> > Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
> > Reviewed-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
> > ---
> >  .../bindings/display/bridge/thine,thc63lvd1024.txt          | 6 ++++++
> >  1 file changed, 6 insertions(+)
> >
> > diff --git a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt b/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt
> > index 37f0c04d5a28..d17d1e5820d7 100644
> > --- a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt
> > +++ b/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.txt
> > @@ -28,6 +28,12 @@ Optional video port nodes:
> >  - port@1: Second LVDS input port
> >  - port@3: Second digital CMOS/TTL parallel output
> >
> > +The device can operate in single-link mode or dual-link mode. In single-link
> > +mode, all pixels are received on port@0, and port@1 shall not contain any
> > +endpoint. In dual-link mode, even-numbered pixels are received on port@0 and
> > +odd-numbered pixels on port@1, and both port@0 and port@1 shall contain
> > +endpoints.
> 
> This describes single/dual input.
> Does single/dual output need to be described, too?

Jacopo asked the same question on v1 :-) Dual-output should be described
as well, but as I have no hardware setup where to test that, I decided
to leave it out of the DT bindings to start with, as it's generally a
bad idea to specify untested DT bindings (as in having no end-to-end
implementation). I don't think it will be a big deal though, there is
already a port for the second output, it should just be a matter of
connecting it.

> BTW, I see the second input/output set is optional, wile the first set
> is required.  Could it happen the hardware is wired for the second
> set only?

Not to my knowledge. In dual-in, dual-out the two input/output pairs are
not independent, the two inputs are used together to create a higher
bandwidth link, and the odd- and even-pixels are then sent to separate
routes.

-- 
Regards,

Laurent Pinchart
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 02/10] dt-bindings: display: bridge: thc63lvd1024: Document dual-link operation

[Rob Herring]

On Sun, 12 May 2019 00:06:54 +0300, Laurent Pinchart wrote:
> The THC63LVD1024 LVDS decoder can operate in two modes, single-link or
> dual-link. In dual-link mode both input ports are used to carry even-
> and odd-numbered pixels separately. Document this in the DT bindings,
> along with the related rules governing port and usage.
> 
> Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
> Reviewed-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
> ---
>  .../bindings/display/bridge/thine,thc63lvd1024.txt          | 6 ++++++
>  1 file changed, 6 insertions(+)
> 

Reviewed-by: Rob Herring <robh@kernel.org>
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 04/10] dt-bindings: display: renesas: lvds: Add renesas,companion property

[Jacopo Mondi]

[-- Attachment #1.1: Type: text/plain, Size: 1918 bytes --]

Hi Laurent,

On Sun, May 12, 2019 at 12:06:56AM +0300, Laurent Pinchart wrote:
> Add a new optional renesas,companion property to point to the companion
> LVDS encoder. This is used to support dual-link operation where the main
> LVDS encoder splits even-numbered and odd-numbered pixels between the
> two LVDS encoders.
>
> The new property doesn't control the mode of operation, it only
> describes the relationship between the master and companion LVDS
> encoders.
>
> Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
> ---
> Changes since v1:
>
> - Fixed typo
> ---
>  .../devicetree/bindings/display/bridge/renesas,lvds.txt     | 6 ++++++
>  1 file changed, 6 insertions(+)
>
> diff --git a/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt b/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt
> index 900a884ad9f5..f2cc01d54cbd 100644
> --- a/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt
> +++ b/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt
> @@ -45,6 +45,12 @@ OF graph bindings specified in Documentation/devicetree/bindings/graph.txt.
>
>  Each port shall have a single endpoint.
>
> +Optional properties:
> +
> +- renesas,companion : phandle to the companion LVDS encoder. This property is
> +  valid for the first LVDS encoder on D3 and E3 SoCs only, and points to the
> +  second encoder to be used as a companion in dual-link mode.
> +

If I got this right, the property does not enable dual-link
operations by itself, but it needs the next bridge to be operating in
dual link mode (ie. has both LVDS0 and LVDS1 output connected to its
input ports). Is it worth describing it here (or at least clarify the
the property alone does not enable dual link operations).

Apart from that
Reviewed-by: Jacopo Mondi <jacopo+renesas@jmondi.org>

Thanks
   j


>
>  Example:
>
> --
> Regards,
>
> Laurent Pinchart
>

[-- Attachment #1.2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 00/10] R-Car DU: LVDS dual-link mode support

[Jacopo Mondi]

[-- Attachment #1.1: Type: text/plain, Size: 6274 bytes --]

Hi Laurent,

On Sun, May 12, 2019 at 12:06:52AM +0300, Laurent Pinchart wrote:
> Hello everybody,
>
> This patch series implements support for LVDS dual-link mode in the
> R-Car DU and R-Car LVDS encoder drivers, and well as in the thc63lvd1024
> LVDS decoder driver.
>
> LVDS dual-link is a mode of operation where two individual LVDS links
> are operated together to carry even- and odd-numbered pixels separately.
> This doubles the possible bandwidth of the video transmission. Both the
> transmitter and the receiver need to support this mode of operation.
>
> The R-Car D3 and E3 SoCs include two independent LVDS encoders that can
> be grouped together to operate in dual-link mode. When used separately,
> the LVDS encoders are connected to two different CRTCs and transmit
> independent video streams. When used in dual-link mode, the first LVDS
> encoder is connected to the first CRTC, and split even- and odd-numbered
> pixels. It transmits half of the pixels on its LVDS output, and sends
> the other half to the second LVDS encoder for transmittion over the
> second LVDS link. The second LVDS encoder thus operates under control of
> the first one, and isn't connected directly to a CRTC.
>
> On the receiving side, the THC63LVD1024 LVDS-to-parallel bridge has two
> LVDS inputs and two parallel outputs. It can operate in four different
> modes:
>
> - Single-in, single-out: The first LVDS input receives the video stream,
>   and the bridge outputs it on the first parallel output. The second
>   LVDS input and the second parallel output are not used.
>
> - Single-in, dual-out: The first LVDS input receives the video stream,
>   and the bridge splits even- and odd-numbered pixels and outputs them
>   on the first and second parallel outputs. The second LVDS input is not
>   used.
>
> - Dual-in, single-out: The two LVDS inputs are used in dual-link mode,
>   and the bridge combines the even- and odd-numbered pixels and outputs
>   them on the first parallel output. The second parallel output is not
>   used.
>
> - Dual-in, dual-out: The two LVDS inputs are used in dual-link mode,
>   and the bridge outputs the even- and odd-numbered pixels on the first
>   parallel output.
>
> The operating mode is selected by two input pins of the bridge, which
> are connected to DIP switches on the development boards I use. The mode
> is thus fixed from a Linux point of view.
>
> Patch 01/10 adds a new dual_link boolen field to the drm_bridge_timings
> structure to let bridges report their LVDS mode of operation. Patch
> 02/10 clarifies the THC63LVD1024 DT bindings to document dual-link
> operation, and patch 03/10 implements dual-link support in the
> thc64lvd1024 bridge driver by setting the drm_bridge_timings dual_link
> field according to the mode selected through DT.
>
> Patch 04/10 extends the R-Car LVDS DT bindings to specify the companion
> LVDS encoder for dual-link operation. Patches 05/10 then performs a
> small cleanup in the LVDS encoder driver. Patch 06/10 implements
> dual-link support in the LVDS encoder driver, which involves retrieving
> the operation mode from the LVDS receiver, locating the companion LVDS
> encoder, and configuring both encoders when dual-link operation is
> desired. The API towards the DU driver is also extended to report the
> mode of operation.
>
> Patch 07/10 implements dual-link mode support in the DU driver. There is
> no specific configuration to be performed there, as dual-link is fully
> implemented in the LVDS encoder driver, but the DU driver has to skip
> creation of the DRM encoder and connector related to the second LVDS
> encoder when dual-link is used, as the second LVDS encoder operates as a
> slave of the first one, transparently from a CRTC (and thus userspace)
> perspective.
>
> Patch 08/10 specifies the companion LVDS encoder in the D3 and E3 DT
> bindings. This by itself doesn't enable dual-link mode, the LVDS0
> encoder is still connected to the HDMI output through LVDS receiver, and
> the LVDS1 encoder is not used. Patches 09/10 and 10/10, not intended to
> be merged, enable dual-link operation for the D3 and E3 boards for
> testing and require flipping DIP switches on the boards.
>
> The patches are based on top of my drm/du/next branch, and are available
> for convenience at
>
>         git://linuxtv.org/pinchartl/media.git drm/du/lvds/dual-link
>
> They have been tested successfully on the D3 Draak board. I expect them
> to work on E3 as well, but I don't have access to an Ebisu board to test
> this.

I have now tested the series on E3 Ebisu board using kms-tests using
the HDMI output and I confirm it works as expected.

For the whole series:
Tested-by: Jacopo Mondi <jacopo+renesas@jmondi.org>

Thanks
  j

>
> Laurent Pinchart (10):
>   drm: bridge: Add dual_link field to the drm_bridge_timings structure
>   dt-bindings: display: bridge: thc63lvd1024: Document dual-link
>     operation
>   drm: bridge: thc63: Report input bus mode through bridge timings
>   dt-bindings: display: renesas: lvds: Add renesas,companion property
>   drm: rcar-du: lvds: Remove LVDS double-enable checks
>   drm: rcar-du: lvds: Add support for dual-link mode
>   drm: rcar-du: Skip LVDS1 output on Gen3 when using dual-link LVDS mode
>   arm64: dts: renesas: r8a7799[05]: Point LVDS0 to its companion LVDS1
>   [HACK] arm64: dts: renesas: draak: Enable LVDS dual-link operation
>   [HACK] arm64: dts: renesas: ebisu: Enable LVDS dual-link operation
>
>  .../bindings/display/bridge/renesas,lvds.txt  |   6 +
>  .../display/bridge/thine,thc63lvd1024.txt     |   6 +
>  .../arm64/boot/dts/renesas/r8a77990-ebisu.dts |  21 ++-
>  arch/arm64/boot/dts/renesas/r8a77990.dtsi     |   2 +
>  .../arm64/boot/dts/renesas/r8a77995-draak.dts |  21 ++-
>  arch/arm64/boot/dts/renesas/r8a77995.dtsi     |   2 +
>  drivers/gpu/drm/bridge/thc63lvd1024.c         |  54 ++++++--
>  drivers/gpu/drm/rcar-du/rcar_du_encoder.c     |  12 ++
>  drivers/gpu/drm/rcar-du/rcar_du_kms.c         |   2 +-
>  drivers/gpu/drm/rcar-du/rcar_lvds.c           | 123 +++++++++++++-----
>  drivers/gpu/drm/rcar-du/rcar_lvds.h           |   5 +
>  include/drm/drm_bridge.h                      |   8 ++
>  12 files changed, 214 insertions(+), 48 deletions(-)
>
> --
> Regards,
>
> Laurent Pinchart
>

[-- Attachment #1.2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 04/10] dt-bindings: display: renesas: lvds: Add renesas,companion property

[Laurent Pinchart]

Hi Jacopo,

On Tue, May 28, 2019 at 11:28:47AM +0200, Jacopo Mondi wrote:
> On Sun, May 12, 2019 at 12:06:56AM +0300, Laurent Pinchart wrote:
> > Add a new optional renesas,companion property to point to the companion
> > LVDS encoder. This is used to support dual-link operation where the main
> > LVDS encoder splits even-numbered and odd-numbered pixels between the
> > two LVDS encoders.
> >
> > The new property doesn't control the mode of operation, it only
> > describes the relationship between the master and companion LVDS
> > encoders.
> >
> > Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
> > ---
> > Changes since v1:
> >
> > - Fixed typo
> > ---
> >  .../devicetree/bindings/display/bridge/renesas,lvds.txt     | 6 ++++++
> >  1 file changed, 6 insertions(+)
> >
> > diff --git a/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt b/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt
> > index 900a884ad9f5..f2cc01d54cbd 100644
> > --- a/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt
> > +++ b/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt
> > @@ -45,6 +45,12 @@ OF graph bindings specified in Documentation/devicetree/bindings/graph.txt.
> >
> >  Each port shall have a single endpoint.
> >
> > +Optional properties:
> > +
> > +- renesas,companion : phandle to the companion LVDS encoder. This property is
> > +  valid for the first LVDS encoder on D3 and E3 SoCs only, and points to the
> > +  second encoder to be used as a companion in dual-link mode.
> > +
> 
> If I got this right, the property does not enable dual-link
> operations by itself, but it needs the next bridge to be operating in
> dual link mode (ie. has both LVDS0 and LVDS1 output connected to its
> input ports).

Correct.

> Is it worth describing it here (or at least clarify the the property
> alone does not enable dual link operations).

How about the following ?

- renesas,companion : phandle to the companion LVDS encoder. This property is
  mandatory for the first LVDS encoder on D3 and E3 SoCs, and shall point to 
  the second encoder to be used as a companion in dual-link mode. It shall not 
  be set for any other LVDS encoder.

> Apart from that
> Reviewed-by: Jacopo Mondi <jacopo+renesas@jmondi.org>

-- 
Regards,

Laurent Pinchart
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel