[PATCH v9 0/3] media: nxp: Add CSI Pixel Formatter support

[PATCH v9 0/3] media: nxp: Add CSI Pixel Formatter support

[Guoniu Zhou]

CSI Pixel Formatter is a module found on i.MX95. It could unpack the
pixels received by the formatter and reformat them to meet the pixel
link format requirement.

This patch series adds a new V4L2 driver for CSI Pixel Formatter.

v4l2-compliance 1.28.1-5233, 64 bits, 64-bit time_t
v4l2-compliance SHA: fc15e229d9d3 2024-07-23 19:22:15

Compliance test for device /dev/v4l-subdev9:

Driver Info:
	Driver version   : 7.1.0
	Capabilities     : 0x00000002
		Streams Support
	Client Capabilities: 0x0000000000000003
streams interval-uses-which
Required ioctls:
	test VIDIOC_SUDBEV_QUERYCAP: OK
	test invalid ioctls: OK

Allow for multiple opens:
	test second /dev/v4l-subdev9 open: OK
	test VIDIOC_SUBDEV_QUERYCAP: OK
	test for unlimited opens: OK

Debug ioctls:
	test VIDIOC_LOG_STATUS: OK (Not Supported)

Input ioctls:
	test VIDIOC_G/S_TUNER/ENUM_FREQ_BANDS: OK (Not Supported)
	test VIDIOC_G/S_FREQUENCY: OK (Not Supported)
	test VIDIOC_S_HW_FREQ_SEEK: OK (Not Supported)
	test VIDIOC_ENUMAUDIO: OK (Not Supported)
	test VIDIOC_G/S/ENUMINPUT: OK (Not Supported)
	test VIDIOC_G/S_AUDIO: OK (Not Supported)
	Inputs: 0 Audio Inputs: 0 Tuners: 0

Output ioctls:
	test VIDIOC_G/S_MODULATOR: OK (Not Supported)
	test VIDIOC_G/S_FREQUENCY: OK (Not Supported)
	test VIDIOC_ENUMAUDOUT: OK (Not Supported)
	test VIDIOC_G/S/ENUMOUTPUT: OK (Not Supported)
	test VIDIOC_G/S_AUDOUT: OK (Not Supported)
	Outputs: 0 Audio Outputs: 0 Modulators: 0

Input/Output configuration ioctls:
	test VIDIOC_ENUM/G/S/QUERY_STD: OK (Not Supported)
	test VIDIOC_ENUM/G/S/QUERY_DV_TIMINGS: OK (Not Supported)
	test VIDIOC_DV_TIMINGS_CAP: OK (Not Supported)
	test VIDIOC_G/S_EDID: OK (Not Supported)

Sub-Device routing ioctls:
	test Try VIDIOC_SUBDEV_G_ROUTING/VIDIOC_SUBDEV_S_ROUTING: OK
	test Active VIDIOC_SUBDEV_G_ROUTING/VIDIOC_SUBDEV_S_ROUTING: OK

Control ioctls:
	test VIDIOC_QUERY_EXT_CTRL/QUERYMENU: OK (Not Supported)
	test VIDIOC_QUERYCTRL: OK (Not Supported)
	test VIDIOC_G/S_CTRL: OK (Not Supported)
	test VIDIOC_G/S/TRY_EXT_CTRLS: OK (Not Supported)
	test VIDIOC_(UN)SUBSCRIBE_EVENT/DQEVENT: OK (Not Supported)
	test VIDIOC_G/S_JPEGCOMP: OK (Not Supported)
	Standard Controls: 0 Private Controls: 0

Format ioctls:
	test VIDIOC_ENUM_FMT/FRAMESIZES/FRAMEINTERVALS: OK (Not Supported)
	test VIDIOC_G/S_PARM: OK (Not Supported)
	test VIDIOC_G_FBUF: OK (Not Supported)
	test VIDIOC_G_FMT: OK (Not Supported)
	test VIDIOC_TRY_FMT: OK (Not Supported)
	test VIDIOC_S_FMT: OK (Not Supported)
	test VIDIOC_G_SLICED_VBI_CAP: OK (Not Supported)
	test Cropping: OK (Not Supported)
	test Composing: OK (Not Supported)
	test Scaling: OK (Not Supported)

Codec ioctls:
	test VIDIOC_(TRY_)ENCODER_CMD: OK (Not Supported)
	test VIDIOC_G_ENC_INDEX: OK (Not Supported)
	test VIDIOC_(TRY_)DECODER_CMD: OK (Not Supported)

Buffer ioctls:
	test VIDIOC_REQBUFS/CREATE_BUFS/QUERYBUF: OK (Not Supported)
	test CREATE_BUFS maximum buffers: OK
	test VIDIOC_REMOVE_BUFS: OK
	test VIDIOC_EXPBUF: OK (Not Supported)
	test Requests: OK (Not Supported)

Total for device /dev/v4l-subdev9: 47, Succeeded: 47, Failed: 0, Warnings: 0

Signed-off-by: Guoniu Zhou <guoniu.zhou@nxp.com>
---
Changes in v9:
- [NEW PATCH] Fix formatter as syscon child node issue
- Link to v8: https://lore.kernel.org/r/20260525-csi_formatter-v8-0-6b646231224b@oss.nxp.com

Changes in v8:
- Rebase to latest media/next
- Use standard port reference instead of video-interfaces.yaml
- Add parent syscon node in example to show device integration
- Remove fmt field and look up format from subdev state instead
- Unify function and structure naming to use csi_formatter_ prefix
- Remove misleading alignment comment from set_fmt function
- Optimize get_frame_desc to call once per start_stream
- Replace V4L2_FRAME_DESC_ENTRY_MAX with CSI_FORMATTER_VC_NUM in loops
- Remove redundant debug message in enable_streams
- Use MEDIA_PAD_FL_MUST_CONNECT flag instead of manual link check
- Link to v7: https://lore.kernel.org/r/20260518-csi_formatter-v7-0-562b750557e3@oss.nxp.com

Changes in v7:
- Change compatible to imx95-csi-formatter as IP is i.MX95 specific per Marco's suggestion
  Link: https://lore.kernel.org/linux-media/20260511-csi_formatter-v6-0-01028e312e2b@oss.nxp.com/T/#mcd135b3de179b3cb69daa1fd6e0e8e27c85b3332
- Update references from imx9 to imx95 for consistency with dt-bindings
- Enable PM runtime before async registration
- Link to v6: https://lore.kernel.org/r/20260511-csi_formatter-v6-0-01028e312e2b@oss.nxp.com

Changes in v6:
- Rebase to latest media/next
- Update v4l2-compliace test
- Remove unused header includes
- Unify macro naming: VCx/VCX -> VC and parameter x -> vc
- Remove unused format field from csi_formatter struct
- Use compact initialization for formats array
- Make find_csi_format() return NULL instead of default format
- Use unsigned int for array index in find_csi_format()
- Add err_ prefix to error handling labels
- Add v4l2_subdev_cleanup() and reorder cleanup sequence
- Update enable_streams debug output format
- Rename VC_MAX to VC_NUM and fix boundary check
- Update CSI formatter Kconfig description
- Use v4l2_subdev_get_frame_desc_passthrough() helper
- Fix error paths in async registration and probe
- Add mutex to protect enabled_streams
- Switch to devm_pm_runtime_enable()
- Remove redundant num_routes check in set_routing
- Optimize get_index_by_dt() and add warning for unsupported type
- csi_formatter_start/stop_stream: Process all streams in mask
- Link to v5: https://lore.kernel.org/r/20260123-csi_formatter-v5-0-d5b803f867bf@nxp.com

Changes in v5:
- Remove CSI_FORMATTER_DRV_NAME macro since only use once.
- Remove sd->owner = THIS_MODULE;
- Simplify code by using DEFINE_RUNTIME_DEV_PM_OPS macro.
- Link to v4: https://lore.kernel.org/r/20260122-csi_formatter-v4-0-6f6fcad1c33a@nxp.com

Changes in v4:
- Rebase to latest media/next.
- Add comments to describe the index field in formatter_dt_to_index_map array.
- Link to v3: https://lore.kernel.org/r/20251219-csi_formatter-v3-0-8680d6d87091@nxp.com

Changes in v3:
- Rename nxp,imx9-csi-formatter.yaml to fsl,imx9-csi-formatter.yaml.
- Drop clock-names property.
- Drop macro IMX95_PD_CAMERA definition and use a constant directly.
  [PATCH 1/2] media: dt-bindings: Add CSI Pixel Formatter DT bindings
- Remove the assignment driver.owner = THIS_MODULE.
- Assign struct fwnode_handle *ep __free(fwnode_handle) when definition.
- Update yaml file name for csi formatter in MAINTAINERS.
  [PATCH 2/2] media: nxp: Add i.MX9 CSI pixel formatter v4l2 driver
- Link to v2: https://lore.kernel.org/r/20251217-csi_formatter-v2-0-62168af80210@nxp.com

Changes in v2:
- Delete "|" for description key. 
- Add empty line between child node and property.
- Delete labels for endpoint of child nodes.
  [PATCH 1/2] media: dt-bindings: Add CSI Pixel Formatter DT bindings

- Update commit message.
- Use the value defined by bellow macros directly since they are used only once.
  #define CSI_FORMATTER_DEF_MBUS_CODE	MEDIA_BUS_FMT_UYVY8_1X16
  #define CSI_FORMATTER_DEF_PIX_WIDTH	1920U
  #define CSI_FORMATTER_DEF_PIX_HEIGHT	1080U
  #define CSI_FORMATTER_MAX_PIX_WIDTH	0xffff
  #define CSI_FORMATTER_MAX_PIX_HEIGHT	0xffff
- Use macro pm_ptr() to fix build warning when CONFIG_PM is disabled. 
- Finish route loop by break statement, instead of goto.
- Return dev_err_probe() when meet errors in probe() function instead of dev_err().
- Remove MODULE_ALIAS().
- Refine .enable(.dsable)_stream callback implementation, include bellow changes:
  Add stream checking.
  Fix potential pm runtime count unbalance issue.
  Add stop stream error handling when enabling remote subdev stream.
- Use __free(fwnode_handle) to drop reference to a device node automatically.
  [PATCH 2/2] media: nxp: Add i.MX9 CSI pixel formatter v4l2 driver

- Link to v1: https://lore.kernel.org/r/20251203-csi_formatter-v1-0-eb9e1147b49e@nxp.com

---
Guoniu Zhou (3):
      dt-bindings: clock: imx95-blk-ctl: Allow child nodes
      media: dt-bindings: Add CSI Pixel Formatter DT bindings
      media: nxp: Add i.MX95 CSI pixel formatter v4l2 driver

 .../bindings/clock/nxp,imx95-blk-ctl.yaml          |  11 +
 .../bindings/media/fsl,imx95-csi-formatter.yaml    |  96 +++
 MAINTAINERS                                        |   8 +
 drivers/media/platform/nxp/Kconfig                 |  14 +
 drivers/media/platform/nxp/Makefile                |   1 +
 drivers/media/platform/nxp/imx95-csi-formatter.c   | 758 +++++++++++++++++++++
 6 files changed, 888 insertions(+)
---
base-commit: a3d78e74dd3ed04797ea351edb7f0a19b961c063
change-id: 20251125-csi_formatter-e6d29316dce6

Best regards,
-- 
Guoniu Zhou <guoniu.zhou@oss.nxp.com>

[PATCH v9 1/3] dt-bindings: clock: imx95-blk-ctl: Allow child nodes

[Guoniu Zhou]

Add support for child nodes in the imx95-blk-ctl binding to match
the driver implementation which calls devm_of_platform_populate().

Add #address-cells, #size-cells properties and patternProperties
to allow child device nodes with their own bindings.

Signed-off-by: Guoniu Zhou <guoniu.zhou@oss.nxp.com>
---
Changes in v9:
- New patch to address the issue of formatter acting as a child node of syscon
---
 .../devicetree/bindings/clock/nxp,imx95-blk-ctl.yaml          | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/Documentation/devicetree/bindings/clock/nxp,imx95-blk-ctl.yaml b/Documentation/devicetree/bindings/clock/nxp,imx95-blk-ctl.yaml
index 27403b4c52d6..33ad1c15cc9c 100644
--- a/Documentation/devicetree/bindings/clock/nxp,imx95-blk-ctl.yaml
+++ b/Documentation/devicetree/bindings/clock/nxp,imx95-blk-ctl.yaml
@@ -39,6 +39,17 @@ properties:
       ID in its "clocks" phandle cell. See
       include/dt-bindings/clock/nxp,imx95-clock.h
 
+  '#address-cells':
+    const: 1
+
+  '#size-cells':
+    const: 1
+
+patternProperties:
+  "^.*@[0-9a-f]+$":
+    type: object
+    description: Child nodes with their own bindings
+
 required:
   - compatible
   - reg

-- 
2.34.1

[PATCH v9 2/3] media: dt-bindings: Add CSI Pixel Formatter DT bindings

[Guoniu Zhou]

From: Guoniu Zhou <guoniu.zhou@nxp.com>

The i.MX95 CSI pixel formatting module uses packet info, pixel and
non-pixel data from the CSI-2 host controller and reformat them to
match Pixel Link(PL) definition.

Reviewed-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Guoniu Zhou <guoniu.zhou@nxp.com>
---
Changes in v8:
- Use standard port reference instead of video-interfaces.yaml
- Add parent syscon node in example to show device integration
- Add required constraints for port@0 and port@1 in ports node

Changes in v7:
- Change compatible to imx95-csi-formatter as IP is i.MX95 specific per Marco's suggestion
  Link: https://lore.kernel.org/linux-media/20260511-csi_formatter-v6-0-01028e312e2b@oss.nxp.com/T/#mcd135b3de179b3cb69daa1fd6e0e8e27c85b3332
---
 .../bindings/media/fsl,imx95-csi-formatter.yaml    | 96 ++++++++++++++++++++++
 1 file changed, 96 insertions(+)

diff --git a/Documentation/devicetree/bindings/media/fsl,imx95-csi-formatter.yaml b/Documentation/devicetree/bindings/media/fsl,imx95-csi-formatter.yaml
new file mode 100644
index 000000000000..61068ea0a69a
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/fsl,imx95-csi-formatter.yaml
@@ -0,0 +1,96 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/fsl,imx95-csi-formatter.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: i.MX95 CSI Pixel Formatter
+
+maintainers:
+  - Guoniu Zhou <guoniu.zhou@nxp.com>
+
+description:
+  The CSI pixel formatting module found on i.MX95 uses packet info, pixel
+  and non-pixel data from the CSI-2 host controller and reformat them to
+  match Pixel Link(PL) definition.
+
+properties:
+  compatible:
+    const: fsl,imx95-csi-formatter
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
+  ports:
+    $ref: /schemas/graph.yaml#/properties/ports
+
+    properties:
+      port@0:
+        $ref: /schemas/graph.yaml#/properties/port
+        description: MIPI CSI-2 RX IDI interface
+
+      port@1:
+        $ref: /schemas/graph.yaml#/properties/port
+        description: Pixel Link Interface
+
+    required:
+      - port@0
+      - port@1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - power-domains
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/nxp,imx95-clock.h>
+
+    syscon@4c100000 {
+        compatible = "nxp,imx95-camera-csr", "syscon";
+        reg = <0x4ac10000 0x10000>;
+        #address-cells = <1>;
+        #size-cells = <1>;
+        #clock-cells = <1>;
+        clocks = <&scmi_clk 62>;
+        power-domains = <&scmi_devpd 3>;
+
+        formatter@20{
+            compatible = "fsl,imx95-csi-formatter";
+            reg = <0x20 0x100>;
+            clocks = <&cameramix_csr IMX95_CLK_CAMBLK_CSI2_FOR0>;
+            power-domains = <&scmi_devpd 3>;
+
+            ports {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                port@0 {
+                    reg = <0>;
+
+                    endpoint {
+                        remote-endpoint = <&mipi_csi_0_out>;
+                    };
+
+               };
+
+                port@1 {
+                    reg = <1>;
+
+                    endpoint {
+                        remote-endpoint = <&isi_in_2>;
+                    };
+                };
+            };
+        };
+    };

-- 
2.34.1

[PATCH v9 3/3] media: nxp: Add i.MX95 CSI pixel formatter v4l2 driver

[Guoniu Zhou]

From: Guoniu Zhou <guoniu.zhou@nxp.com>

The CSI pixel formatter is a module found on i.MX95 used to reformat
packet info, pixel and non-pixel data from CSI-2 host controller to
match Pixel Link(PL) definition.

Add data formatting support.

Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Guoniu Zhou <guoniu.zhou@nxp.com>
---
Changes in v8:
- Remove fmt field and look up format from subdev state instead
- Unify function and structure naming to use csi_formatter_ prefix
- Remove misleading alignment comment from set_fmt function
- Optimize get_frame_desc to call once per start_stream
- Replace V4L2_FRAME_DESC_ENTRY_MAX with CSI_FORMATTER_VC_NUM in loops
- Remove redundant debug message in enable_streams
- Use MEDIA_PAD_FL_MUST_CONNECT flag instead of manual link check
- Fix typo: Formater -> Formatter in Kconfig help text
- Improve grammar in data type index mapping comment

Changes in v7:
- Update references from imx9 to imx95 for consistency with dt-bindings
- Enable PM runtime before async registration

Changes in v6:
- Remove unused header includes
- Unify macro naming: VCx/VCX -> VC and parameter x -> vc
- Remove unused format field from csi_formatter struct
- Use compact initialization for formats array
- Make find_csi_format() return NULL instead of default format
- Use unsigned int for array index in find_csi_format()
- Add err_ prefix to error handling labels
- Add v4l2_subdev_cleanup() and reorder cleanup sequence
- Update enable_streams debug output format
- Rename VC_MAX to VC_NUM and fix boundary check
- Update CSI formatter Kconfig description
- Use v4l2_subdev_get_frame_desc_passthrough() helper
- Fix error paths in async registration and probe
- Add mutex to protect enabled_streams
- Switch to devm_pm_runtime_enable()
- Remove redundant num_routes check in set_routing
- Optimize get_index_by_dt() and add warning for unsupported type
- csi_formatter_start/stop_stream: Process all streams in mask
---
 MAINTAINERS                                      |   8 +
 drivers/media/platform/nxp/Kconfig               |  14 +
 drivers/media/platform/nxp/Makefile              |   1 +
 drivers/media/platform/nxp/imx95-csi-formatter.c | 758 +++++++++++++++++++++++
 4 files changed, 781 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 3124500ff432..5229b75d930a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19269,6 +19269,14 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/media/nxp,imx8-jpeg.yaml
 F:	drivers/media/platform/nxp/imx-jpeg
 
+NXP i.MX 95 CSI PIXEL FORMATTER V4L2 DRIVER
+M:	Guoniu Zhou <guoniu.zhou@nxp.com>
+L:	imx@lists.linux.dev
+L:	linux-media@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/media/fsl,imx95-csi-formatter.yaml
+F:	drivers/media/platform/nxp/imx95-csi-formatter.c
+
 NXP i.MX CLOCK DRIVERS
 M:	Abel Vesa <abelvesa@kernel.org>
 R:	Peng Fan <peng.fan@nxp.com>
diff --git a/drivers/media/platform/nxp/Kconfig b/drivers/media/platform/nxp/Kconfig
index 40e3436669e2..1eccf128d149 100644
--- a/drivers/media/platform/nxp/Kconfig
+++ b/drivers/media/platform/nxp/Kconfig
@@ -28,6 +28,20 @@ config VIDEO_IMX8MQ_MIPI_CSI2
 	  Video4Linux2 driver for the MIPI CSI-2 receiver found on the i.MX8MQ
 	  SoC.
 
+config VIDEO_IMX95_CSI_FORMATTER
+	tristate "NXP i.MX95 CSI Pixel Formatter driver"
+	depends on ARCH_MXC || COMPILE_TEST
+	depends on VIDEO_DEV
+	select MEDIA_CONTROLLER
+	select V4L2_FWNODE
+	select VIDEO_V4L2_SUBDEV_API
+	help
+	  This driver provides support for the CSI Pixel Formatter found on
+	  i.MX95 series SoCs. This module unpacks the pixels received from the
+	  CSI-2 interface and reformats them to meet pixel link requirements.
+
+	  Say Y here to enable CSI Pixel Formatter module for i.MX95 SoC.
+
 config VIDEO_IMX_MIPI_CSIS
 	tristate "NXP MIPI CSI-2 CSIS receiver found on i.MX7 and i.MX8 models"
 	depends on ARCH_MXC || COMPILE_TEST
diff --git a/drivers/media/platform/nxp/Makefile b/drivers/media/platform/nxp/Makefile
index 4d90eb713652..6410115d870e 100644
--- a/drivers/media/platform/nxp/Makefile
+++ b/drivers/media/platform/nxp/Makefile
@@ -6,6 +6,7 @@ obj-y += imx8-isi/
 
 obj-$(CONFIG_VIDEO_IMX7_CSI) += imx7-media-csi.o
 obj-$(CONFIG_VIDEO_IMX8MQ_MIPI_CSI2) += imx8mq-mipi-csi2.o
+obj-$(CONFIG_VIDEO_IMX95_CSI_FORMATTER) += imx95-csi-formatter.o
 obj-$(CONFIG_VIDEO_IMX_MIPI_CSIS) += imx-mipi-csis.o
 obj-$(CONFIG_VIDEO_IMX_PXP) += imx-pxp.o
 obj-$(CONFIG_VIDEO_MX2_EMMAPRP) += mx2_emmaprp.o
diff --git a/drivers/media/platform/nxp/imx95-csi-formatter.c b/drivers/media/platform/nxp/imx95-csi-formatter.c
new file mode 100644
index 000000000000..9dee38d85839
--- /dev/null
+++ b/drivers/media/platform/nxp/imx95-csi-formatter.c
@@ -0,0 +1,758 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2025 NXP
+ */
+
+#include <linux/bits.h>
+#include <linux/clk.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+
+#include <media/mipi-csi2.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-fwnode.h>
+#include <media/v4l2-mc.h>
+#include <media/v4l2-subdev.h>
+
+/* CSI Pixel Formatter registers map */
+
+#define CSI_VC_INTERLACED_LINE_CNT(vc)		(0x00 + (vc) * 0x04)
+#define INTERLACED_ODD_LINE_CNT_SET(x)		FIELD_PREP(GENMASK(13, 0), (x))
+#define INTERLACED_EVEN_LINE_CNT_SET(x)		FIELD_PREP(GENMASK(29, 16), (x))
+
+#define CSI_VC_INTERLACED_CTRL			0x20
+
+#define CSI_VC_INTERLACED_ERR			0x24
+#define CSI_VC_ERR_MASK				GENMASK(7, 0)
+#define CSI_VC_ERR(vc)				BIT((vc))
+
+#define CSI_VC_YUV420_FIRST_LINE_EVEN		0x28
+#define YUV420_FIRST_LINE_EVEN(vc)		BIT((vc))
+
+#define CSI_RAW32_CTRL				0x30
+#define CSI_VC_RAW32_MODE(vc)			BIT((vc))
+#define CSI_VC_RAW32_SWAP_MODE(vc)		BIT((vc) + 8)
+
+#define CSI_STREAM_FENCING_CTRL			0x34
+#define CSI_VC_STREAM_FENCING(vc)		BIT((vc))
+#define CSI_VC_STREAM_FENCING_RST(vc)		BIT((vc) + 8)
+
+#define CSI_STREAM_FENCING_STS			0x38
+#define CSI_STREAM_FENCING_STS_MASK		GENMASK(7, 0)
+
+#define CSI_VC_NON_PIXEL_DATA_TYPE(vc)		(0x40 + (vc) * 0x04)
+
+#define CSI_VC_PIXEL_DATA_CTRL(vc)		(0x60 + (vc) * 0x04)
+#define NEW_VC(vc)				FIELD_PREP(GENMASK(3, 1), vc)
+#define REROUTE_VC_ENABLE			BIT(0)
+
+#define CSI_VC_ROUTE_PIXEL_DATA_TYPE(vc)	(0x80 + (vc) * 0x04)
+
+#define CSI_VC_NON_PIXEL_DATA_CTRL(vc)		(0xa0 + (vc) * 0x04)
+
+#define CSI_VC_PIXEL_DATA_TYPE(vc)		(0xc0 + (vc) * 0x04)
+
+#define CSI_VC_PIXEL_DATA_TYPE_ERR(vc)		(0xe0 + (vc) * 0x04)
+
+#define CSI_FORMATTER_PAD_SINK			0
+#define CSI_FORMATTER_PAD_SOURCE		1
+#define CSI_FORMATTER_PAD_NUM			2
+
+#define CSI_FORMATTER_VC_NUM			8 /* Number of virtual channels */
+
+struct csi_formatter_pix_format {
+	u32 code;
+	u32 data_type;
+};
+
+struct csi_formatter {
+	struct device *dev;
+	struct regmap *regs;
+	struct clk *clk;
+
+	struct v4l2_subdev sd;
+	struct v4l2_subdev *csi_sd;
+	struct v4l2_async_notifier notifier;
+	struct media_pad pads[CSI_FORMATTER_PAD_NUM];
+
+	u32 remote_pad;
+	u32 reg_offset;
+
+	/* Protects enabled_streams */
+	struct mutex lock;
+	u64 enabled_streams;
+};
+
+struct csi_formatter_dt_index {
+	u8 dtype;
+	u8 index;
+};
+
+/*
+ * The index corresponds to the bit index in the register that enables
+ * the data type of pixel data transported by the Formatter.
+ */
+static const struct csi_formatter_dt_index formatter_dt_to_index_map[] = {
+	{ .dtype = MIPI_CSI2_DT_YUV420_8B,        .index = 0 },
+	{ .dtype = MIPI_CSI2_DT_YUV420_8B_LEGACY, .index = 2 },
+	{ .dtype = MIPI_CSI2_DT_YUV422_8B,        .index = 6 },
+	{ .dtype = MIPI_CSI2_DT_RGB444,		  .index = 8 },
+	{ .dtype = MIPI_CSI2_DT_RGB555,           .index = 9 },
+	{ .dtype = MIPI_CSI2_DT_RGB565,           .index = 10 },
+	{ .dtype = MIPI_CSI2_DT_RGB666,           .index = 11 },
+	{ .dtype = MIPI_CSI2_DT_RGB888,           .index = 12 },
+	{ .dtype = MIPI_CSI2_DT_RAW6,             .index = 16 },
+	{ .dtype = MIPI_CSI2_DT_RAW7,             .index = 17 },
+	{ .dtype = MIPI_CSI2_DT_RAW8,             .index = 18 },
+	{ .dtype = MIPI_CSI2_DT_RAW10,            .index = 19 },
+	{ .dtype = MIPI_CSI2_DT_RAW12,            .index = 20 },
+	{ .dtype = MIPI_CSI2_DT_RAW14,            .index = 21 },
+	{ .dtype = MIPI_CSI2_DT_RAW16,            .index = 22 },
+};
+
+static const struct csi_formatter_pix_format formats[] = {
+	/* YUV formats */
+	{ MEDIA_BUS_FMT_UYVY8_1X16,	MIPI_CSI2_DT_YUV422_8B },
+	/* RGB formats */
+	{ MEDIA_BUS_FMT_RGB565_1X16,	MIPI_CSI2_DT_RGB565 },
+	{ MEDIA_BUS_FMT_RGB888_1X24,	MIPI_CSI2_DT_RGB888 },
+	/* RAW (Bayer and greyscale) formats */
+	{ MEDIA_BUS_FMT_SBGGR8_1X8,	MIPI_CSI2_DT_RAW8 },
+	{ MEDIA_BUS_FMT_SGBRG8_1X8,	MIPI_CSI2_DT_RAW8 },
+	{ MEDIA_BUS_FMT_SGRBG8_1X8,	MIPI_CSI2_DT_RAW8 },
+	{ MEDIA_BUS_FMT_SRGGB8_1X8,	MIPI_CSI2_DT_RAW8 },
+	{ MEDIA_BUS_FMT_Y8_1X8,		MIPI_CSI2_DT_RAW8 },
+	{ MEDIA_BUS_FMT_SBGGR10_1X10,	MIPI_CSI2_DT_RAW10 },
+	{ MEDIA_BUS_FMT_SGBRG10_1X10,	MIPI_CSI2_DT_RAW10 },
+	{ MEDIA_BUS_FMT_SGRBG10_1X10,	MIPI_CSI2_DT_RAW10 },
+	{ MEDIA_BUS_FMT_SRGGB10_1X10,	MIPI_CSI2_DT_RAW10 },
+	{ MEDIA_BUS_FMT_Y10_1X10,	MIPI_CSI2_DT_RAW10 },
+	{ MEDIA_BUS_FMT_SBGGR12_1X12,	MIPI_CSI2_DT_RAW12 },
+	{ MEDIA_BUS_FMT_SGBRG12_1X12,	MIPI_CSI2_DT_RAW12 },
+	{ MEDIA_BUS_FMT_SGRBG12_1X12,	MIPI_CSI2_DT_RAW12 },
+	{ MEDIA_BUS_FMT_SRGGB12_1X12,	MIPI_CSI2_DT_RAW12 },
+	{ MEDIA_BUS_FMT_Y12_1X12,	MIPI_CSI2_DT_RAW12 },
+	{ MEDIA_BUS_FMT_SBGGR14_1X14,	MIPI_CSI2_DT_RAW14 },
+	{ MEDIA_BUS_FMT_SGBRG14_1X14,	MIPI_CSI2_DT_RAW14 },
+	{ MEDIA_BUS_FMT_SGRBG14_1X14,	MIPI_CSI2_DT_RAW14 },
+	{ MEDIA_BUS_FMT_SRGGB14_1X14,	MIPI_CSI2_DT_RAW14 },
+	{ MEDIA_BUS_FMT_SBGGR16_1X16,	MIPI_CSI2_DT_RAW16 },
+	{ MEDIA_BUS_FMT_SGBRG16_1X16,	MIPI_CSI2_DT_RAW16 },
+	{ MEDIA_BUS_FMT_SGRBG16_1X16,	MIPI_CSI2_DT_RAW16 },
+	{ MEDIA_BUS_FMT_SRGGB16_1X16,	MIPI_CSI2_DT_RAW16 },
+};
+
+static const struct v4l2_mbus_framefmt formatter_default_fmt = {
+	.code = MEDIA_BUS_FMT_UYVY8_1X16,
+	.width = 1920U,
+	.height = 1080U,
+	.field = V4L2_FIELD_NONE,
+	.colorspace = V4L2_COLORSPACE_SMPTE170M,
+	.xfer_func = V4L2_MAP_XFER_FUNC_DEFAULT(V4L2_COLORSPACE_SMPTE170M),
+	.ycbcr_enc = V4L2_MAP_YCBCR_ENC_DEFAULT(V4L2_COLORSPACE_SMPTE170M),
+	.quantization = V4L2_QUANTIZATION_LIM_RANGE,
+};
+
+static const struct csi_formatter_pix_format *csi_formatter_find_format(u32 code)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(formats); i++)
+		if (code == formats[i].code)
+			return &formats[i];
+
+	return NULL;
+}
+
+/* -----------------------------------------------------------------------------
+ * V4L2 subdev operations
+ */
+
+static inline struct csi_formatter *sd_to_formatter(struct v4l2_subdev *sdev)
+{
+	return container_of(sdev, struct csi_formatter, sd);
+}
+
+static int __csi_formatter_subdev_set_routing(struct v4l2_subdev *sd,
+					      struct v4l2_subdev_state *state,
+					      struct v4l2_subdev_krouting *routing)
+{
+	int ret;
+
+	ret = v4l2_subdev_routing_validate(sd, routing,
+					   V4L2_SUBDEV_ROUTING_ONLY_1_TO_1);
+	if (ret)
+		return ret;
+
+	return v4l2_subdev_set_routing_with_fmt(sd, state, routing,
+						&formatter_default_fmt);
+}
+
+static int csi_formatter_subdev_init_state(struct v4l2_subdev *sd,
+					   struct v4l2_subdev_state *sd_state)
+{
+	struct v4l2_subdev_route routes[] = {
+		{
+			.sink_pad = CSI_FORMATTER_PAD_SINK,
+			.sink_stream = 0,
+			.source_pad = CSI_FORMATTER_PAD_SOURCE,
+			.source_stream = 0,
+			.flags = V4L2_SUBDEV_ROUTE_FL_ACTIVE,
+		},
+	};
+
+	struct v4l2_subdev_krouting routing = {
+		.num_routes = ARRAY_SIZE(routes),
+		.routes = routes,
+	};
+
+	return __csi_formatter_subdev_set_routing(sd, sd_state, &routing);
+}
+
+static int csi_formatter_subdev_enum_mbus_code(struct v4l2_subdev *sd,
+					       struct v4l2_subdev_state *sd_state,
+					       struct v4l2_subdev_mbus_code_enum *code)
+{
+	if (code->pad == CSI_FORMATTER_PAD_SOURCE) {
+		struct v4l2_mbus_framefmt *fmt;
+
+		if (code->index > 0)
+			return -EINVAL;
+
+		fmt = v4l2_subdev_state_get_format(sd_state, code->pad,
+						   code->stream);
+		code->code = fmt->code;
+		return 0;
+	}
+
+	if (code->index >= ARRAY_SIZE(formats))
+		return -EINVAL;
+
+	code->code = formats[code->index].code;
+
+	return 0;
+}
+
+static int csi_formatter_subdev_set_fmt(struct v4l2_subdev *sd,
+					struct v4l2_subdev_state *sd_state,
+					struct v4l2_subdev_format *sdformat)
+{
+	struct csi_formatter_pix_format const *format;
+	struct v4l2_mbus_framefmt *fmt;
+
+	if (sdformat->pad == CSI_FORMATTER_PAD_SOURCE)
+		return v4l2_subdev_get_fmt(sd, sd_state, sdformat);
+
+	format = csi_formatter_find_format(sdformat->format.code);
+	if (!format)
+		format = &formats[0];
+
+	v4l_bound_align_image(&sdformat->format.width, 1, 0xffff, 2,
+			      &sdformat->format.height, 1, 0xffff, 0, 0);
+
+	fmt = v4l2_subdev_state_get_format(sd_state, sdformat->pad,
+					   sdformat->stream);
+	*fmt = sdformat->format;
+
+	/* Set default code if user set an invalid value */
+	fmt->code = format->code;
+
+	/* Propagate the format from sink stream to source stream */
+	fmt = v4l2_subdev_state_get_opposite_stream_format(sd_state, sdformat->pad,
+							   sdformat->stream);
+	if (!fmt)
+		return -EINVAL;
+
+	*fmt = sdformat->format;
+
+	return 0;
+}
+
+static int csi_formatter_subdev_set_routing(struct v4l2_subdev *sd,
+					    struct v4l2_subdev_state *state,
+					    enum v4l2_subdev_format_whence which,
+					    struct v4l2_subdev_krouting *routing)
+{
+	if (which == V4L2_SUBDEV_FORMAT_ACTIVE &&
+	    media_entity_is_streaming(&sd->entity))
+		return -EBUSY;
+
+	return __csi_formatter_subdev_set_routing(sd, state, routing);
+}
+
+static inline void csi_formatter_write(struct csi_formatter *formatter,
+				       unsigned int reg, unsigned int value)
+{
+	u32 offset = formatter->reg_offset;
+
+	regmap_write(formatter->regs, reg + offset, value);
+}
+
+static u8 csi_formatter_get_index_by_dt(u8 data_type)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(formatter_dt_to_index_map); ++i) {
+		const struct csi_formatter_dt_index *entry =
+			&formatter_dt_to_index_map[i];
+
+		if (data_type == entry->dtype)
+			return entry->index;
+	}
+
+	pr_warn_once("Unsupported data type 0x%x, using default\n", data_type);
+
+	return formatter_dt_to_index_map[0].index;
+}
+
+static int csi_formatter_get_vc(struct csi_formatter *formatter,
+				struct v4l2_mbus_frame_desc *fd,
+				unsigned int stream)
+{
+	struct v4l2_mbus_frame_desc_entry *entry = NULL;
+	unsigned int i;
+	int vc;
+
+	for (i = 0; i < fd->num_entries; ++i) {
+		if (fd->entry[i].stream == stream) {
+			entry = &fd->entry[i];
+			break;
+		}
+	}
+
+	if (!entry) {
+		dev_err(formatter->dev,
+			"No frame desc entry for stream %u\n", stream);
+		return -EPIPE;
+	}
+
+	vc = entry->bus.csi2.vc;
+
+	if (vc < 0 || vc >= CSI_FORMATTER_VC_NUM) {
+		dev_err(formatter->dev, "Invalid virtual channel %d\n", vc);
+		return -EINVAL;
+	}
+
+	return vc;
+}
+
+static void csi_formatter_stop_stream(struct csi_formatter *formatter,
+				      u64 stream_mask)
+{
+	unsigned int i;
+
+	for (i = 0; i < CSI_FORMATTER_VC_NUM; ++i) {
+		if (!(stream_mask & BIT(i)))
+			continue;
+
+		csi_formatter_write(formatter, CSI_VC_PIXEL_DATA_TYPE(i), 0);
+	}
+}
+
+static int csi_formatter_start_stream(struct csi_formatter *formatter,
+				      struct v4l2_subdev_state *state,
+				      u64 stream_mask)
+{
+	const struct csi_formatter_pix_format *pix_fmt;
+	struct v4l2_mbus_framefmt *fmt;
+	struct v4l2_mbus_frame_desc fd = {};
+	u64 configured_streams = 0;
+	unsigned int i;
+	u32 val;
+	int vc;
+	int ret;
+
+	ret = v4l2_subdev_call(formatter->csi_sd, pad, get_frame_desc,
+			       formatter->remote_pad, &fd);
+	if (ret < 0 && ret != -ENOIOCTLCMD) {
+		dev_err(formatter->dev, "Failed to get frame desc: %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < CSI_FORMATTER_VC_NUM; ++i) {
+		if (!(stream_mask & BIT(i)))
+			continue;
+
+		fmt = v4l2_subdev_state_get_format(state,
+						   CSI_FORMATTER_PAD_SINK, i);
+
+		pix_fmt = csi_formatter_find_format(fmt->code);
+
+		val = BIT(csi_formatter_get_index_by_dt(pix_fmt->data_type));
+
+		if (ret == -ENOIOCTLCMD) {
+			/*
+			 * Source doesn't implement get_frame_desc, use
+			 * default VC 0
+			 */
+			vc = 0;
+		} else {
+			vc = csi_formatter_get_vc(formatter, &fd, i);
+			if (vc < 0) {
+				ret = vc;
+				goto err_cleanup;
+			}
+		}
+
+		csi_formatter_write(formatter, CSI_VC_PIXEL_DATA_TYPE(vc), val);
+		configured_streams |= BIT(i);
+	}
+
+	return 0;
+
+err_cleanup:
+	csi_formatter_stop_stream(formatter, configured_streams);
+	return ret;
+}
+
+static int csi_formatter_subdev_enable_streams(struct v4l2_subdev *sd,
+					       struct v4l2_subdev_state *state,
+					       u32 pad, u64 streams_mask)
+{
+	struct csi_formatter *formatter = sd_to_formatter(sd);
+	struct device *dev = formatter->dev;
+	u64 sink_streams;
+	int ret;
+
+	sink_streams = v4l2_subdev_state_xlate_streams(state,
+						       CSI_FORMATTER_PAD_SOURCE,
+						       CSI_FORMATTER_PAD_SINK,
+						       &streams_mask);
+	if (!sink_streams || !streams_mask)
+		return -EINVAL;
+
+	guard(mutex)(&formatter->lock);
+
+	if (!formatter->enabled_streams) {
+		ret = pm_runtime_resume_and_get(formatter->dev);
+		if (ret < 0) {
+			dev_err(dev, "Failed to resume runtime PM: %d\n", ret);
+			return ret;
+		}
+	}
+
+	ret = csi_formatter_start_stream(formatter, state, streams_mask);
+	if (ret)
+		goto err_runtime_put;
+
+	ret = v4l2_subdev_enable_streams(formatter->csi_sd,
+					 formatter->remote_pad,
+					 sink_streams);
+	if (ret)
+		goto err_stop_stream;
+
+	formatter->enabled_streams |= streams_mask;
+
+	return 0;
+
+err_stop_stream:
+	csi_formatter_stop_stream(formatter, streams_mask);
+err_runtime_put:
+	if (!formatter->enabled_streams)
+		pm_runtime_put(formatter->dev);
+	return ret;
+}
+
+static int csi_formatter_subdev_disable_streams(struct v4l2_subdev *sd,
+						struct v4l2_subdev_state *state,
+						u32 pad, u64 streams_mask)
+{
+	struct csi_formatter *formatter = sd_to_formatter(sd);
+	u64 sink_streams;
+	int ret;
+
+	sink_streams = v4l2_subdev_state_xlate_streams(state,
+						       CSI_FORMATTER_PAD_SOURCE,
+						       CSI_FORMATTER_PAD_SINK,
+						       &streams_mask);
+	if (!sink_streams || !streams_mask)
+		return -EINVAL;
+
+	guard(mutex)(&formatter->lock);
+
+	ret = v4l2_subdev_disable_streams(formatter->csi_sd, formatter->remote_pad,
+					  sink_streams);
+	if (ret)
+		dev_err(formatter->dev, "Failed to disable streams: %d\n", ret);
+
+	csi_formatter_stop_stream(formatter, streams_mask);
+
+	formatter->enabled_streams &= ~streams_mask;
+
+	if (!formatter->enabled_streams)
+		pm_runtime_put(formatter->dev);
+
+	return ret;
+}
+
+static const struct v4l2_subdev_pad_ops formatter_subdev_pad_ops = {
+	.enum_mbus_code		= csi_formatter_subdev_enum_mbus_code,
+	.get_fmt		= v4l2_subdev_get_fmt,
+	.set_fmt		= csi_formatter_subdev_set_fmt,
+	.get_frame_desc		= v4l2_subdev_get_frame_desc_passthrough,
+	.set_routing		= csi_formatter_subdev_set_routing,
+	.enable_streams		= csi_formatter_subdev_enable_streams,
+	.disable_streams	= csi_formatter_subdev_disable_streams,
+};
+
+static const struct v4l2_subdev_ops formatter_subdev_ops = {
+	.pad = &formatter_subdev_pad_ops,
+};
+
+static const struct v4l2_subdev_internal_ops formatter_internal_ops = {
+	.init_state = csi_formatter_subdev_init_state,
+};
+
+/* -----------------------------------------------------------------------------
+ * Media entity operations
+ */
+
+static const struct media_entity_operations formatter_entity_ops = {
+	.link_validate	= v4l2_subdev_link_validate,
+	.get_fwnode_pad = v4l2_subdev_get_fwnode_pad_1_to_1,
+};
+
+static int csi_formatter_subdev_init(struct csi_formatter *formatter)
+{
+	struct v4l2_subdev *sd = &formatter->sd;
+	int ret;
+
+	v4l2_subdev_init(sd, &formatter_subdev_ops);
+
+	snprintf(sd->name, sizeof(sd->name), "%s", dev_name(formatter->dev));
+	sd->internal_ops = &formatter_internal_ops;
+
+	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE |
+		     V4L2_SUBDEV_FL_HAS_EVENTS |
+		     V4L2_SUBDEV_FL_STREAMS;
+	sd->entity.function = MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER;
+	sd->entity.ops = &formatter_entity_ops;
+	sd->dev = formatter->dev;
+
+	formatter->pads[CSI_FORMATTER_PAD_SINK].flags = MEDIA_PAD_FL_SINK
+						      | MEDIA_PAD_FL_MUST_CONNECT;
+	formatter->pads[CSI_FORMATTER_PAD_SOURCE].flags = MEDIA_PAD_FL_SOURCE;
+
+	ret = media_entity_pads_init(&sd->entity, CSI_FORMATTER_PAD_NUM,
+				     formatter->pads);
+	if (ret) {
+		dev_err(formatter->dev, "Failed to init pads\n");
+		return ret;
+	}
+
+	ret = v4l2_subdev_init_finalize(sd);
+	if (ret)
+		media_entity_cleanup(&sd->entity);
+
+	return ret;
+}
+
+static inline struct csi_formatter *
+notifier_to_csi_formatter(struct v4l2_async_notifier *n)
+{
+	return container_of(n, struct csi_formatter, notifier);
+}
+
+static int csi_formatter_notify_bound(struct v4l2_async_notifier *notifier,
+				      struct v4l2_subdev *sd,
+				      struct v4l2_async_connection *asc)
+{
+	const unsigned int link_flags = MEDIA_LNK_FL_IMMUTABLE
+				      | MEDIA_LNK_FL_ENABLED;
+	struct csi_formatter *formatter = notifier_to_csi_formatter(notifier);
+	struct v4l2_subdev *sdev = &formatter->sd;
+	struct media_pad *sink = &sdev->entity.pads[CSI_FORMATTER_PAD_SINK];
+	struct media_pad *remote_pad;
+	int ret;
+
+	formatter->csi_sd = sd;
+
+	dev_dbg(formatter->dev, "Bound subdev: %s pad\n", sd->name);
+
+	ret = v4l2_create_fwnode_links_to_pad(sd, sink, link_flags);
+	if (ret < 0)
+		return ret;
+
+	remote_pad = media_pad_remote_pad_first(sink);
+	if (!remote_pad) {
+		dev_err(formatter->dev, "Pipe not setup correctly\n");
+		return -EPIPE;
+	}
+	formatter->remote_pad = remote_pad->index;
+
+	return 0;
+}
+
+static const struct v4l2_async_notifier_operations formatter_notify_ops = {
+	.bound = csi_formatter_notify_bound,
+};
+
+static int csi_formatter_async_register(struct csi_formatter *formatter)
+{
+	struct device *dev = formatter->dev;
+	struct v4l2_async_connection *asc;
+	int ret;
+
+	struct fwnode_handle *ep __free(fwnode_handle) =
+		fwnode_graph_get_endpoint_by_id(dev_fwnode(dev), 0, 0,
+						FWNODE_GRAPH_ENDPOINT_NEXT);
+	if (!ep)
+		return -ENOTCONN;
+
+	v4l2_async_subdev_nf_init(&formatter->notifier, &formatter->sd);
+
+	asc = v4l2_async_nf_add_fwnode_remote(&formatter->notifier, ep,
+					      struct v4l2_async_connection);
+	if (IS_ERR(asc)) {
+		ret = PTR_ERR(asc);
+		goto err_cleanup_notifier;
+	}
+
+	formatter->notifier.ops = &formatter_notify_ops;
+
+	ret = v4l2_async_nf_register(&formatter->notifier);
+	if (ret)
+		goto err_cleanup_notifier;
+
+	ret = v4l2_async_register_subdev(&formatter->sd);
+	if (ret)
+		goto err_unregister_notifier;
+
+	return 0;
+
+err_unregister_notifier:
+	v4l2_async_nf_unregister(&formatter->notifier);
+err_cleanup_notifier:
+	v4l2_async_nf_cleanup(&formatter->notifier);
+	return ret;
+}
+
+static void csi_formatter_async_unregister(struct csi_formatter *formatter)
+{
+	v4l2_async_unregister_subdev(&formatter->sd);
+	v4l2_async_nf_unregister(&formatter->notifier);
+	v4l2_async_nf_cleanup(&formatter->notifier);
+}
+
+/* -----------------------------------------------------------------------------
+ * Suspend/resume
+ */
+
+static int csi_formatter_runtime_suspend(struct device *dev)
+{
+	struct v4l2_subdev *sd = dev_get_drvdata(dev);
+	struct csi_formatter *formatter = sd_to_formatter(sd);
+
+	clk_disable_unprepare(formatter->clk);
+
+	return 0;
+}
+
+static int csi_formatter_runtime_resume(struct device *dev)
+{
+	struct v4l2_subdev *sd = dev_get_drvdata(dev);
+	struct csi_formatter *formatter = sd_to_formatter(sd);
+
+	return clk_prepare_enable(formatter->clk);
+}
+
+static DEFINE_RUNTIME_DEV_PM_OPS(csi_formatter_pm_ops,
+				 csi_formatter_runtime_suspend,
+				 csi_formatter_runtime_resume, NULL);
+
+static int csi_formatter_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct csi_formatter *formatter;
+	u32 val;
+	int ret;
+
+	formatter = devm_kzalloc(dev, sizeof(*formatter), GFP_KERNEL);
+	if (!formatter)
+		return -ENOMEM;
+
+	formatter->dev = dev;
+
+	ret = devm_mutex_init(dev, &formatter->lock);
+	if (ret)
+		return ret;
+
+	formatter->regs = syscon_node_to_regmap(dev->parent->of_node);
+	if (IS_ERR(formatter->regs))
+		return dev_err_probe(dev, PTR_ERR(formatter->regs),
+				     "Failed to get csi formatter regmap\n");
+
+	ret = of_property_read_u32(dev->of_node, "reg", &val);
+	if (ret < 0)
+		return dev_err_probe(dev, ret,
+				     "Failed to get csi formatter reg property\n");
+
+	formatter->reg_offset = val;
+
+	formatter->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(formatter->clk))
+		return dev_err_probe(dev, PTR_ERR(formatter->clk),
+				     "Failed to get pixel clock\n");
+
+	ret = csi_formatter_subdev_init(formatter);
+	if (ret < 0)
+		return dev_err_probe(dev, ret, "Failed to initialize formatter subdev\n");
+
+	platform_set_drvdata(pdev, &formatter->sd);
+
+	/* Enable runtime PM. */
+	ret = devm_pm_runtime_enable(dev);
+	if (ret)
+		goto err_cleanup_subdev;
+
+	ret = csi_formatter_async_register(formatter);
+	if (ret < 0) {
+		dev_err_probe(dev, ret, "Failed to register async subdevice\n");
+		goto err_cleanup_subdev;
+	}
+
+	return 0;
+
+err_cleanup_subdev:
+	v4l2_subdev_cleanup(&formatter->sd);
+	media_entity_cleanup(&formatter->sd.entity);
+	return ret;
+}
+
+static void csi_formatter_remove(struct platform_device *pdev)
+{
+	struct v4l2_subdev *sd = platform_get_drvdata(pdev);
+	struct csi_formatter *formatter = sd_to_formatter(sd);
+
+	csi_formatter_async_unregister(formatter);
+
+	v4l2_subdev_cleanup(&formatter->sd);
+	media_entity_cleanup(&formatter->sd.entity);
+}
+
+static const struct of_device_id csi_formatter_of_match[] = {
+	{ .compatible = "fsl,imx95-csi-formatter" },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, csi_formatter_of_match);
+
+static struct platform_driver csi_formatter_device_driver = {
+	.driver = {
+		.name           = "csi-pixel-formatter",
+		.of_match_table = csi_formatter_of_match,
+		.pm             = pm_ptr(&csi_formatter_pm_ops),
+	},
+	.probe  = csi_formatter_probe,
+	.remove = csi_formatter_remove,
+};
+
+module_platform_driver(csi_formatter_device_driver);
+
+MODULE_AUTHOR("NXP Semiconductor, Inc.");
+MODULE_DESCRIPTION("NXP i.MX95 CSI Pixel Formatter driver");
+MODULE_LICENSE("GPL");

-- 
2.34.1

Re: [PATCH v9 1/3] dt-bindings: clock: imx95-blk-ctl: Allow child nodes

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:

New issues:
- [Medium] The dt-binding fails to allow the `ranges` (and potentially `dma-ranges`) property, causing schema validation to reject valid device tree nodes that map child device registers.
- [Low] Child node `patternProperties` definition lacks the required `additionalProperties` or `unevaluatedProperties` directive.

Pre-existing issues:
- [Critical] The imx95_bc driver completely lacks a `.remove` callback and fails to clean up non-managed resources, leading to critical resource leaks, use-after-free bugs on unbind, and an APB clock leak.
--

commit 726604ca3bd356c1af7395b3121524ccf63624b9
Author: Guoniu Zhou <guoniu.zhou@oss.nxp.com>

dt-bindings: clock: imx95-blk-ctl: Allow child nodes

This commit adds #address-cells, #size-cells, and a patternProperties block
to the imx95-blk-ctl binding. This allows child device nodes to have their
own bindings, matching the driver's use of devm_of_platform_populate().

> Add support for child nodes in the imx95-blk-ctl binding to match
> the driver implementation which calls devm_of_platform_populate().

[Severity: Critical]
This is a pre-existing issue, but does the imx95_bc driver completely lack a
.remove callback?

While looking at the driver implementation mentioned here, it appears it
relies on non-managed APIs (clk_hw_register_mux, clk_hw_register_divider,
of_clk_add_hw_provider) to register clocks but lacks a way to unregister them
on unbind.

Since the clk_hw_data and associated strings are allocated via devm_kzalloc(),
they would be freed on unbind, potentially leaving the clock framework with
pointers to freed structures. Can this result in a use-after-free?

Additionally, when !bc->pdata is true, the probe function leaves bc->clk_apb
enabled without any cleanup mechanism. Does this cause a clock leak on unbind?

> diff --git a/Documentation/devicetree/bindings/clock/nxp,imx95-blk-ctl.yaml b/Documentation/devicetree/bindings/clock/nxp,imx95-blk-ctl.yaml
> index 27403b4c52d62..33ad1c15cc9c8 100644
> --- a/Documentation/devicetree/bindings/clock/nxp,imx95-blk-ctl.yaml
> +++ b/Documentation/devicetree/bindings/clock/nxp,imx95-blk-ctl.yaml
> @@ -39,6 +39,17 @@ properties:
>        ID in its "clocks" phandle cell. See
>        include/dt-bindings/clock/nxp,imx95-clock.h
>  
> +  '#address-cells':
> +    const: 1
> +
> +  '#size-cells':
> +    const: 1

[Severity: Medium]
Since this binding now allows child nodes with #address-cells and #size-cells,
does the parent node also need to allow the ranges property?

Without ranges: true in the properties block, device trees that correctly
define ranges to translate memory-mapped child registers into the CPU address
space might be rejected by dt_binding_check due to the top-level
additionalProperties: false restriction.

> +
> +patternProperties:
> +  "^.*@[0-9a-f]+$":
> +    type: object
> +    description: Child nodes with their own bindings

[Severity: Low]
Does this child node definition need an additionalProperties or
unevaluatedProperties directive?

Device tree schema guidelines typically require all type: object nodes to
explicitly declare one of these. Omitting it might trigger meta-schema
warnings during make dt_binding_check.

> +
>  required:
>    - compatible
>    - reg

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260526-csi_formatter-v9-0-ca3d8c334c39@oss.nxp.com?part=1

Re: [PATCH v9 2/3] media: dt-bindings: Add CSI Pixel Formatter DT bindings

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [Low] Unit address mismatch in the example's syscon parent node.
- [Low] Missing 'ranges' property in the parent syscon node in the example.
- [Low] Poor formatting in the device tree example block.
--

commit 1b3ddadbdea2fb3bc19aa036199bd1e0ef56413b
Author: Guoniu Zhou <guoniu.zhou@nxp.com>

media: dt-bindings: Add CSI Pixel Formatter DT bindings

This commit adds the device tree binding schema for the i.MX95 CSI pixel
formatter module. It defines the constraints and ports required to interface
the CSI-2 host controller with the Pixel Link definition.

> diff --git a/Documentation/devicetree/bindings/media/fsl,imx95-csi-formatter.yaml b/Documentation/devicetree/bindings/media/fsl,imx95-csi-formatter.yaml
> new file mode 100644
> index 0000000000000..61068ea0a69a0
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/media/fsl,imx95-csi-formatter.yaml
[ ... ]
> +examples:
> +  - |
> +    #include <dt-bindings/clock/nxp,imx95-clock.h>
> +
> +    syscon@4c100000 {
> +        compatible = "nxp,imx95-camera-csr", "syscon";
> +        reg = <0x4ac10000 0x10000>;

[Severity: Low]
This isn't a bug, but the unit address in the node name (4c100000) does not
match the base address specified in the reg property (0x4ac10000). Should the
node be named syscon@4ac10000 to match the reg property and avoid unit_address
validation warnings?

> +        #address-cells = <1>;
> +        #size-cells = <1>;
> +        #clock-cells = <1>;
> +        clocks = <&scmi_clk 62>;
> +        power-domains = <&scmi_devpd 3>;

[Severity: Low]
Does this syscon parent node need a ranges property?

Because it specifies address and size cells and contains a memory-mapped
child node (formatter@20), omitting the ranges property prevents correct
address translation for the child node and typically results in dtc warnings.

> +
> +        formatter@20{

[Severity: Low]
This isn't a bug, but there is a missing space before the opening brace.

> +            compatible = "fsl,imx95-csi-formatter";
> +            reg = <0x20 0x100>;
[ ... ]
> +                port@0 {
> +                    reg = <0>;
> +
> +                    endpoint {
> +                        remote-endpoint = <&mipi_csi_0_out>;
> +                    };
> +
> +               };

[Severity: Low]
This isn't a bug, but the closing brace here is indented incorrectly compared
to the rest of the block.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260526-csi_formatter-v9-0-ca3d8c334c39@oss.nxp.com?part=2

Re: [PATCH v9 3/3] media: nxp: Add i.MX95 CSI pixel formatter v4l2 driver

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 8 potential issue(s) to consider:
- [High] Unchecked pointer from `v4l2_subdev_state_get_format()` is dereferenced due to missing stream ID validation.
- [High] The driver incorrectly passes and iterates over the source stream mask to query sink-side formats and frame descriptors.
- [High] `csi_formatter_stop_stream()` clears the wrong hardware register by using the stream index instead of the Virtual Channel (VC) ID.
- [High] The driver leaks the PM runtime usage counter and fails to clean up hardware state if removed while streams are active.
- [High] Error handling in `csi_formatter_subdev_disable_streams()` desynchronizes state with the V4L2 core, causing PM usage counter underflows.
- [Medium] Mixing scope-based cleanup helpers (`__free()` and `guard()`) with `goto` error handling.
- [Medium] Stream start and stop routines inappropriately limit V4L2 stream ID iterations to `CSI_FORMATTER_VC_NUM` (8).
- [Medium] The driver inappropriately returns `-EINVAL` when setting a format on an unrouted sink stream.
--

commit 519af3c273f2310baca55e801417774f1157eba3
Author: Guoniu Zhou <guoniu.zhou@nxp.com>
Date:   Tue May 26 08:57:22 2026 +0000

    media: nxp: Add i.MX95 CSI pixel formatter v4l2 driver
    
    The CSI pixel formatter is a module found on i.MX95 used to reformat
    packet info, pixel and non-pixel data from CSI-2 host controller to
    match Pixel Link(PL) definition.

> diff --git a/drivers/media/platform/nxp/imx95-csi-formatter.c b/drivers/media/platform/nxp/imx95-csi-formatter.c
> new file mode 100644
> index 0000000000000..9dee38d85839c
> --- /dev/null
> +++ b/drivers/media/platform/nxp/imx95-csi-formatter.c

[ ... ]

> +static int csi_formatter_subdev_enum_mbus_code(struct v4l2_subdev *sd,
> +					       struct v4l2_subdev_state *sd_state,
> +					       struct v4l2_subdev_mbus_code_enum *code)
> +{
> +	if (code->pad == CSI_FORMATTER_PAD_SOURCE) {
> +		struct v4l2_mbus_framefmt *fmt;
> +
> +		if (code->index > 0)
> +			return -EINVAL;
> +
> +		fmt = v4l2_subdev_state_get_format(sd_state, code->pad,
> +						   code->stream);
> +		code->code = fmt->code;

[Severity: High]
Is there a missing check for fmt being NULL here? 

If userspace provides an invalid or non-existent stream ID,
v4l2_subdev_state_get_format() will return NULL, which appears to be
unconditionally dereferenced here.

> +		return 0;
> +	}
> +
> +	if (code->index >= ARRAY_SIZE(formats))
> +		return -EINVAL;
> +
> +	code->code = formats[code->index].code;
> +
> +	return 0;
> +}
> +
> +static int csi_formatter_subdev_set_fmt(struct v4l2_subdev *sd,
> +					struct v4l2_subdev_state *sd_state,
> +					struct v4l2_subdev_format *sdformat)
> +{
> +	struct csi_formatter_pix_format const *format;
> +	struct v4l2_mbus_framefmt *fmt;
> +
> +	if (sdformat->pad == CSI_FORMATTER_PAD_SOURCE)
> +		return v4l2_subdev_get_fmt(sd, sd_state, sdformat);
> +
> +	format = csi_formatter_find_format(sdformat->format.code);
> +	if (!format)
> +		format = &formats[0];
> +
> +	v4l_bound_align_image(&sdformat->format.width, 1, 0xffff, 2,
> +			      &sdformat->format.height, 1, 0xffff, 0, 0);
> +
> +	fmt = v4l2_subdev_state_get_format(sd_state, sdformat->pad,
> +					   sdformat->stream);
> +	*fmt = sdformat->format;

[Severity: High]
Could fmt be NULL here as well if an invalid stream ID is provided?

> +
> +	/* Set default code if user set an invalid value */
> +	fmt->code = format->code;
> +
> +	/* Propagate the format from sink stream to source stream */
> +	fmt = v4l2_subdev_state_get_opposite_stream_format(sd_state, sdformat->pad,
> +							   sdformat->stream);
> +	if (!fmt)
> +		return -EINVAL;

[Severity: Medium]
Should this return -EINVAL if the stream is unrouted? 

The V4L2 specification requires format changes on unrouted streams to succeed
(they just shouldn't propagate), so returning an error here might break
compliant userspace applications configuring unrouted pad formats.

> +
> +	*fmt = sdformat->format;
> +
> +	return 0;
> +}

[ ... ]

> +static void csi_formatter_stop_stream(struct csi_formatter *formatter,
> +				      u64 stream_mask)
> +{
> +	unsigned int i;
> +
> +	for (i = 0; i < CSI_FORMATTER_VC_NUM; ++i) {

[Severity: Medium]
Is it safe to limit V4L2 stream ID iterations to CSI_FORMATTER_VC_NUM (8)?

V4L2 stream IDs are arbitrary and can range from 0 to 63, so any
configured stream with an ID >= 8 would be silently ignored. Could
this use for_each_set_bit() to iterate over the entire mask instead?

> +		if (!(stream_mask & BIT(i)))
> +			continue;
> +
> +		csi_formatter_write(formatter, CSI_VC_PIXEL_DATA_TYPE(i), 0);

[Severity: High]
Does this write to the correct hardware register?

csi_formatter_start_stream() correctly resolves the hardware Virtual
Channel (VC) from the remote frame descriptor, but here we seem to be
writing 0 to CSI_VC_PIXEL_DATA_TYPE(i) where i is the V4L2 stream index.

If the stream index and VC ID differ, could this clear the wrong register
and corrupt another running VC's state?

> +	}
> +}
> +
> +static int csi_formatter_start_stream(struct csi_formatter *formatter,
> +				      struct v4l2_subdev_state *state,
> +				      u64 stream_mask)
> +{
> +	const struct csi_formatter_pix_format *pix_fmt;
> +	struct v4l2_mbus_framefmt *fmt;
> +	struct v4l2_mbus_frame_desc fd = {};
> +	u64 configured_streams = 0;
> +	unsigned int i;
> +	u32 val;
> +	int vc;
> +	int ret;
> +
> +	ret = v4l2_subdev_call(formatter->csi_sd, pad, get_frame_desc,
> +			       formatter->remote_pad, &fd);
> +	if (ret < 0 && ret != -ENOIOCTLCMD) {
> +		dev_err(formatter->dev, "Failed to get frame desc: %d\n", ret);
> +		return ret;
> +	}
> +
> +	for (i = 0; i < CSI_FORMATTER_VC_NUM; ++i) {
> +		if (!(stream_mask & BIT(i)))
> +			continue;
> +
> +		fmt = v4l2_subdev_state_get_format(state,
> +						   CSI_FORMATTER_PAD_SINK, i);
> +
> +		pix_fmt = csi_formatter_find_format(fmt->code);

[Severity: High]
In csi_formatter_subdev_enable_streams(), stream_mask originates from the
source pad, but it is passed here and used as the stream index (i) to fetch
the sink-side format.

If the routing maps a different sink stream ID to this source stream ID,
will v4l2_subdev_state_get_format() return NULL for the non-existent sink
stream i and cause a NULL pointer dereference when accessing fmt->code?

> +
> +		val = BIT(csi_formatter_get_index_by_dt(pix_fmt->data_type));
> +
> +		if (ret == -ENOIOCTLCMD) {
> +			/*
> +			 * Source doesn't implement get_frame_desc, use
> +			 * default VC 0
> +			 */
> +			vc = 0;
> +		} else {
> +			vc = csi_formatter_get_vc(formatter, &fd, i);
> +			if (vc < 0) {
> +				ret = vc;
> +				goto err_cleanup;
> +			}
> +		}
> +
> +		csi_formatter_write(formatter, CSI_VC_PIXEL_DATA_TYPE(vc), val);
> +		configured_streams |= BIT(i);
> +	}
> +
> +	return 0;
> +
> +err_cleanup:
> +	csi_formatter_stop_stream(formatter, configured_streams);
> +	return ret;
> +}
> +
> +static int csi_formatter_subdev_enable_streams(struct v4l2_subdev *sd,
> +					       struct v4l2_subdev_state *state,
> +					       u32 pad, u64 streams_mask)
> +{
> +	struct csi_formatter *formatter = sd_to_formatter(sd);
> +	struct device *dev = formatter->dev;
> +	u64 sink_streams;
> +	int ret;
> +
> +	sink_streams = v4l2_subdev_state_xlate_streams(state,
> +						       CSI_FORMATTER_PAD_SOURCE,
> +						       CSI_FORMATTER_PAD_SINK,
> +						       &streams_mask);
> +	if (!sink_streams || !streams_mask)
> +		return -EINVAL;
> +
> +	guard(mutex)(&formatter->lock);

[Severity: Medium]
Is it intended to mix scope-based cleanup helpers (guard) with goto error
handling here? 

The kernel cleanup subsystem guidelines mandate that goto-based error handling
and scope-based cleanups should never be mixed within the same function.

> +
> +	if (!formatter->enabled_streams) {
> +		ret = pm_runtime_resume_and_get(formatter->dev);
> +		if (ret < 0) {
> +			dev_err(dev, "Failed to resume runtime PM: %d\n", ret);
> +			return ret;
> +		}
> +	}
> +
> +	ret = csi_formatter_start_stream(formatter, state, streams_mask);
> +	if (ret)
> +		goto err_runtime_put;
> +
> +	ret = v4l2_subdev_enable_streams(formatter->csi_sd,
> +					 formatter->remote_pad,
> +					 sink_streams);
> +	if (ret)
> +		goto err_stop_stream;
> +
> +	formatter->enabled_streams |= streams_mask;
> +
> +	return 0;
> +
> +err_stop_stream:
> +	csi_formatter_stop_stream(formatter, streams_mask);
> +err_runtime_put:
> +	if (!formatter->enabled_streams)
> +		pm_runtime_put(formatter->dev);
> +	return ret;
> +}
> +
> +static int csi_formatter_subdev_disable_streams(struct v4l2_subdev *sd,
> +						struct v4l2_subdev_state *state,
> +						u32 pad, u64 streams_mask)
> +{
> +	struct csi_formatter *formatter = sd_to_formatter(sd);
> +	u64 sink_streams;
> +	int ret;
> +
> +	sink_streams = v4l2_subdev_state_xlate_streams(state,
> +						       CSI_FORMATTER_PAD_SOURCE,
> +						       CSI_FORMATTER_PAD_SINK,
> +						       &streams_mask);
> +	if (!sink_streams || !streams_mask)
> +		return -EINVAL;
> +
> +	guard(mutex)(&formatter->lock);
> +
> +	ret = v4l2_subdev_disable_streams(formatter->csi_sd, formatter->remote_pad,
> +					  sink_streams);
> +	if (ret)
> +		dev_err(formatter->dev, "Failed to disable streams: %d\n", ret);
> +
> +	csi_formatter_stop_stream(formatter, streams_mask);
> +
> +	formatter->enabled_streams &= ~streams_mask;
> +
> +	if (!formatter->enabled_streams)
> +		pm_runtime_put(formatter->dev);

[Severity: High]
If v4l2_subdev_disable_streams() fails and returns an error, the V4L2 core keeps
its internal stream state as "enabled", but this function proceeds to clear
formatter->enabled_streams and calls pm_runtime_put().

If the V4L2 core later retries disabling the stream, will it trigger an
unbalanced, secondary pm_runtime_put() call resulting in a PM usage counter
underflow since enabled_streams is already 0?

> +
> +	return ret;
> +}

[ ... ]

> +static int csi_formatter_async_register(struct csi_formatter *formatter)
> +{
> +	struct device *dev = formatter->dev;
> +	struct v4l2_async_connection *asc;
> +	int ret;
> +
> +	struct fwnode_handle *ep __free(fwnode_handle) =
> +		fwnode_graph_get_endpoint_by_id(dev_fwnode(dev), 0, 0,
> +						FWNODE_GRAPH_ENDPOINT_NEXT);

[Severity: Medium]
Does this mix __free(fwnode_handle) with goto error handling below?

Similar to csi_formatter_subdev_enable_streams(), kernel guidelines state that
scope-based cleanup helpers and goto should not be used in the same function.

> +	if (!ep)
> +		return -ENOTCONN;
> +
> +	v4l2_async_subdev_nf_init(&formatter->notifier, &formatter->sd);
> +
> +	asc = v4l2_async_nf_add_fwnode_remote(&formatter->notifier, ep,
> +					      struct v4l2_async_connection);
> +	if (IS_ERR(asc)) {
> +		ret = PTR_ERR(asc);
> +		goto err_cleanup_notifier;
> +	}
> +
> +	formatter->notifier.ops = &formatter_notify_ops;
> +
> +	ret = v4l2_async_nf_register(&formatter->notifier);
> +	if (ret)
> +		goto err_cleanup_notifier;
> +
> +	ret = v4l2_async_register_subdev(&formatter->sd);
> +	if (ret)
> +		goto err_unregister_notifier;
> +
> +	return 0;
> +
> +err_unregister_notifier:
> +	v4l2_async_nf_unregister(&formatter->notifier);
> +err_cleanup_notifier:
> +	v4l2_async_nf_cleanup(&formatter->notifier);
> +	return ret;
> +}

[ ... ]

> +static void csi_formatter_remove(struct platform_device *pdev)
> +{
> +	struct v4l2_subdev *sd = platform_get_drvdata(pdev);
> +	struct csi_formatter *formatter = sd_to_formatter(sd);
> +
> +	csi_formatter_async_unregister(formatter);
> +
> +	v4l2_subdev_cleanup(&formatter->sd);
> +	media_entity_cleanup(&formatter->sd.entity);
> +}

[Severity: High]
If the subdevice is unbound via sysfs while streams are active, will this leak
the PM usage counter and leave the hardware in an active state?

It looks like csi_formatter_remove() unconditionally unregisters the subdevice
but doesn't check if hardware streams need to be stopped or if the PM usage
counter needs to be dropped.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260526-csi_formatter-v9-0-ca3d8c334c39@oss.nxp.com?part=3