Linux-PHY Archive on lore.kernel.org

* [PATCH v6 0/2] phy: qcom-mipi-csi2: Add a CSI2 MIPI DPHY driver
From: Bryan O'Donoghue @ 2026-05-21 12:20 UTC (permalink / raw)
  To: Vinod Koul, Kishon Vijay Abraham I, Rob Herring,
	Krzysztof Kozlowski, Conor Dooley, Neil Armstrong
  Cc: Bryan O'Donoghue, Vladimir Zapolskiy, linux-arm-msm,
	linux-phy, linux-media, devicetree, linux-kernel,
	Bryan O'Donoghue

Changes in v6:
- Taking feedback from lively debate added ports and
  endpoints to the PHY - Neil, Vlad
- Detection of split mode by way of which ports are declared.
  port@0 is always a sensor input.
  port@1 is optional and if present implies split-mode
  port@2 is always the output. - Dmitry, Neil, Vlad.
- Split mode is left as -ENOTSUPP unless/until someone with the appropriate
  hardware can take on responsibility to drive to completion.
- Extending phy_config_opts dropped.
  I think this is a worthwhile extension but this series no longer depends
  on it so dropped. - Bryan
- MX/MXC.
  Two OPP tables one for CSIPHY0/1/2 scaling MXC one for CSIPHY4 keeping
  MXA at LOWSVS_D1 - to be implemented in DT not here. Taniya, Konrad, Bryan
- Changed MAINTAINERS from Supported to Maintained.
  Hobby time for me right now. - Bryan
- Link to v5: https://lore.kernel.org/r/20260326-x1e-csi2-phy-v5-0-0c0fc7f5c01b@linaro.org

v5:
- Adds support to apply passed parameters for clock/data position/polarity - Neil
- Drops GEN1/GEN2 differentiation this can be reconstituted if GEN1 ever
  gets supported in this driver - Dmitry
- Drops camnoc_axi, cpas_ahb - Konrad
- Renames csiphy->core csiphy_timer->timer - Konrad
- Renames rail from 0p8 to 0p9 schematics say  VDD_A_CSI_n_0P9 - Konrad
- TITAN_TOP_GDSC dropped - Konrad
- Passes PHY_QCOM_CSI2_MODE_{DPHY|CPHY|SPLIT_DPHY} with the controller
  selecting the mode. Only DPHY mode is supported but the method to pass
  CPHY or split-mode DPHY configuration is there.
  Since split-mode is a Qualcomm specific mode the PHY modes are defined in
  our binding instead of adding a new type to include/linux/phy/phy.h - bod
- Depends-on: https://lore.kernel.org/r/20260325-dphy-params-extension-v1-0-c6df5599284a@linaro.org
- Link to v4: https://lore.kernel.org/r/20260315-x1e-csi2-phy-v4-0-90c09203888d@linaro.org

v4:
- MMCX, MCX and MX/MXA power-domains added - Dmitry, Vijay, Konrad
- power-domain-names added as required - bod
- opp-tables amended to capture RPMHPD deps - Dmitry, Vijay
- Switched to dev_pm_opp_set_rate, dev_pm_domain_attach_by_name etc
  dropped inherited CAMSS code - Dmitry
- Amended parameters structure to specify power-domain name list - bod
- Removed dead defines - Dmitry
- Noted in CSIPHY commit log intention to rework patterns of
  PHY lane configs into loops/defines/bit-fields later - Dmitry, bod
- Lowercase hex throughout - Dmitry
- The yaml and code in this driver doesn't care if the node is a
  sibling or a sub-node of CAMSS confirmed to work both ways - Dmitry, bod
- Link to v3: https://lore.kernel.org/r/20260226-x1e-csi2-phy-v3-0-11e608759410@linaro.org

v3:

- Resending this to make clear this submission is additive to x1e/Hamoa
  The existing bindings and code will continue to work 
  Bindings are added only, nothing is subtracted from existing ABI.
- Link to v2: https://lore.kernel.org/r/20260225-x1e-csi2-phy-v2-0-7756edb67ea9@linaro.org

v2:

In this updated version

- Added operating-point support
  The csiphy clock sets the OPP prior to setting the rate
  for csiphy and csiphy_timer - Konrad

- Combo mode
  Combo mode in CAMSS yaml has been added. Right now
  no code has been changed in the PHY driver to support it as
  I don't have hardware to test. In principle though it can
  be supported. - Vladimir

- CSIPHY init sequences
  I left these as their "magic number formats". With my diminished
  status as a non-qcom VPN person - I can no longer see what the bits
  map to. Moreover this is the situation any non-VPN community member
  will be in when submitting CSIPHY sequences derived from downstream.

  I think it is perfectly reasonable to take public CSIPHY init sequences
  as magic numbers. If someone with bit-level access wants to enumerate
  the bits that's fine but, it shouldn't gate in the interim. - Konrad/bod

- Sensor endpoints
  I've stuck to the format used by every other CSIPHY in upstream.
  Sensor endpoints hit the CAMSS/CSID endpoint not a endpoint in the PHY.
  Given the proposed changes to CAMSS though to support "combo mode" I
  think this should achieve the same outcome - multiple sensors on the one
  PHY without introducing endpoints into the PHY that no other CSIPHY in
  upstream currently has.

- Bitmask of enabled lanes
  Work needs to be done in the v4l2 layer to really support this.
  I propose making a separate series dedicated to non-linear bit
  interpretation after merging this so as to contain the scope of the
  series to something more bite (byte haha) sized. - Konrad/bod

- Link to v1: https://lore.kernel.org/r/20250710-x1e-csi2-phy-v1-0-74acbb5b162b@linaro.org

v1:
This short series adds a CSI2 MIPI PHY driver, initially supporting D-PHY
mode. The core logic and init sequences come directly from CAMSS and are
working on at least five separate x1e devices.

The rationale to instantiate CSI2 PHYs as standalone devices instead of as
sub-nodes of CAMSS is as follows.

1. Precedence
   CAMSS has a dedicated I2C bus called CCI Camera Control Interface.
   We model this controller as its own separate device in devicetree.
   This makes sense and CCI/I2C is a well defined bus type already modelled
   in Linux.

   MIPI CSI2 PHY devices similarly fit into a well defined separate
   bus/device structure.

   Contrast to another CAMSS component such as VFE, CSID or TPG these
   components only interact with other CAMSS inputs/outputs unlike CSIPHY
   which interacts with non-SoC components.

2. Hardware pinouts and rails
   The CSI2 PHY has its own data/clock lanes out from the SoC and indeed
   has its own incoming power-rails.

3. Other devicetree schemas
   There are several examples throughout the kernel of CSI PHYs modeled as
   standalone devices which one assumes follows the same reasoning as given
   above.

I've been working on this on-and-off since the end of April:
Link: https://lore.kernel.org/linux-media/c5cf0155-f839-4db9-b865-d39b56bb1e0a@linaro.org

There is another proposal to have the PHYs be subdevices of CAMSS but, I
believe we should go with a "full fat" PHY to match best practices in
drivers/phy/qualcomm/*.

Using the standard PHY API and the parameter passing that goes with it
allows us to move away from custom interfaces in CAMSS and to conform more
clearly to established PHY paradigms such as the QMP combo PHY.

Looking at existing compat strings I settled on
"qcom,x1e80100-mipi-csi2-combo-phy" deliberately omitting reference to the
fact the PHY is built on a four nano-meter process node, which seems to
match recent submissions to QMP PHY.

My first pass at this driver included support for the old two phase
devices:

Link: https://git.codelinaro.org/bryan.odonoghue/kernel/-/commit/a504c28d109296c93470340cfe7281231f573bcb#b6e59ed7db94c9da22e492bb03fcda6a4300983c

I realised that the device tree schema changes required to support a
comprehensive conversion of all CAMSS to this driver would be an
almost certainly be unacceptable ABI break or at the very least an enormous
amount of work and verification so I instead aimed to support just one new
SoC in the submission.

I've retained the callback indirections give us scope to add in another type of
future PHY including potentially adding in the 2PH later on.

This driver is tested and working on x1e/Hamoa and has been tested as not
breaking sc8280xp/Makena and sm8250/Kona.

Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
---
Bryan O'Donoghue (2):
      dt-bindings: phy: qcom: Add CSI2 C-PHY/DPHY schema
      phy: qcom-mipi-csi2: Add a CSI2 MIPI DPHY driver

 .../bindings/phy/qcom,x1e80100-csi2-phy.yaml       | 205 ++++++++++++
 MAINTAINERS                                        |  10 +
 drivers/phy/qualcomm/Kconfig                       |  13 +
 drivers/phy/qualcomm/Makefile                      |   5 +
 drivers/phy/qualcomm/phy-qcom-mipi-csi2-3ph-dphy.c | 361 ++++++++++++++++++++
 drivers/phy/qualcomm/phy-qcom-mipi-csi2-core.c     | 368 +++++++++++++++++++++
 drivers/phy/qualcomm/phy-qcom-mipi-csi2.h          |  94 ++++++
 7 files changed, 1056 insertions(+)
---
base-commit: a1db83cc6f7e88a166c77d9060507ec01d617784
change-id: 20250710-x1e-csi2-phy-f6434b651d3a

Best regards,
--  
Bryan O'Donoghue <bryan.odonoghue@linaro.org>

-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

^ permalink raw reply