[PATCH v6 0/5] iio: dac: Add support for AD5529R DAC

[PATCH v6 0/5] iio: dac: Add support for AD5529R DAC

[Janani Sunil]

This patch series adds support for Analog Devices AD5529R, a 16 channel
16 and 12 bit voltage Digital-to-Analog Converter (DAC) with integrated
precision reference. The AD5529R operates from both unipolar and
bipolar supplies. The device communicates via SPI interface.

**Device Overview:**
The AD5529R features 16 independent DAC channels, with 16 or 12 bit
resolution, allowing independently programmable output ranges. The
internal 4.096V precision reference sets the accuracy of the output
voltage.

The device can encode a hardware address in its SPI command frame,
allowing up to 4 devices to share a single chip select. This series
introduces a generic spi-device-addr property for describing this type
of addressing. Existing equivalent properties in the Microchip MCP3564
and MCP3911 bindings are retained but marked as deprecated.

**Features Implemented:**
- Support for AD5529R 12-bit and 16-bit variants via device match data.
- Support for a single DAC device using any hardware address between 0
  and 3.
- Reset support via reset controller framework.
- Dual regmap configuration to handle 8 and 16 bit registers.
- Per-channel output range configuration from devicetree.
- Optional external reference and bipolar supply handling.

**Patch Summary:**
1. Add the generic spi-device-addr SPI peripheral property.
2. Add spi-device-addr to the MCP3564 binding and deprecate its legacy
   vendor specific property.
3. Add spi-device-addr to the MCP3911 binding and deprecate its legacy
   vendor specific property.
4. AD5529R binding documentation with channel configuration.
5. Implement AD5529R IIO DAC Driver with regmap support.

**Testing:**
The driver was compiled and tested on the EVAL-AD5529R-ARDZ using a
coraZ7 with a mainline v7.0 kernel.

**Driver Rationale:**
AD5529R introduces:
1. A unique register layout
2. Mixed 8-bit and 16-bit register accesses
3. Hardware specific features like function generators, multi-die
hotpath registers etc.

The device warrants its own driver due to these fundamental
architectural differences, that would require substantial changes to
existing drivers without providing reusable benefits. The standalone
driver also allows future extensions for related devices in the same
family.

**Not Implemented in this Series:**
The binding includes generic, peripheral level device addressing needed for
multi-device support using a shared CS, but the driver presently
supports only a single device.

Signed-off-by: Janani Sunil <janani.sunil@analog.com>
---
Changes in v6:
- Rename spi,device-addr to spi-device-addr and define it as an array at
  peripheral node level.
- Fix the SPI binding patch subject prefix to use "spi: dt-bindings:".
- Add spi-device-addr to the MCP3564 and MCP3911 bindings.
- Deprecate the existing Microchip-specific device-address properties.
- Replace adi,output-range-microvolt with output-range-microvolt.
- Move AD5529R device addressing from channel nodes to the peripheral
  node.
- Include linux/types.h
- Honour non-zero hardware address in the AD5529R driver.
- Dynamically expose only the channels described by devicetree and
  remove unused scan type definitions.
- Use explicit reset assertion and deassertion as the GPIO reset
  controller does not implement reset_control_reset().
- Use the MICRO and MILLI unit constants when matching output ranges.
-  Simplify optional reference regulator handling and remove the
   external reference comment.
- Simplify error messages and stick to 80 col.
- Link to v5: https://lore.kernel.org/r/20260701-ad5529r-driver-v5-0-ed087900e642@analog.com

Changes in v5:
- Move register bitfield definitions next to their parent register
  addresses.
- Remove spurious extra indent.
- Rename ad5529r_output_ranges_mv[] to ad5529r_output_ranges_mV[].
- Remove extra parentheses in regmap_reg_range() for the readback range.
- Use reset_control_reset() instead of reset_control_deassert().
- Use 10 * USEC_PER_MSEC instead of a bare 10000 in fsleep().
- Use fwnode_property_present() to explicitly guard the optional property.
- Rewrite external_vref detection using explicit if/else.
- Follow reverse christmas tree variable declaration order.
- Improve invalid channel error message to include the maximum.
- Add a new spi property to include the SPI device address.
- Update ad5529r devicetree binding to allow more than 16 channels to include multiple DACs.
- Update cover letter to add a mention about the multi device support.
- Update driver commit message to describe the device further.
- Link to v4: https://lore.kernel.org/r/20260609-ad5529r-driver-v4-0-2e4c02234a1a@analog.com

Changes in v4:
- Fix DT child-node regex for hexadecimal channel addresses.
- Wrap long DT binding description lines.
- Simplify optional `vref-supply` and `hvss-supply` handling.
- Update REF_SEL programming for optional external reference use.
- Clean up range parsing and error messages.
- Simplify debugfs register access by calling regmap helpers directly.
- Add clarifying comments for reset settling time and RAW reads from `DAC_INPUT_A`.
- Remove an unused vref regulator pointer and an include.
- Rename the REF_SEL bit define and clean up small driver details.
- Toggle pins defined as PWM pins, instead of GPIOs
- Update cover letter to sync up latest changes.
- Link to v3: https://lore.kernel.org/r/20260519-ad5529r-driver-v3-0-267c0731aa68@analog.com

Changes in v3:
- Split into adi,ad5529r-16 and adi,ad5529r-12 device tree compatibles
- Add DT-based output range configuration via adi,output-range-microvolt
- Expand DT binding: vref-supply, clear/tg GPIOs, interrupts, muxout
- Correct power supply voltage specifications as per datasheet
- Reduce SPI frequency limit to 25MHz as per datasheet specs
- Switch to autoincrement addressing mode, remove +1 register offsets
- Use DT match data instead of device ID detection for fallback support
- Implement dynamic scale/offset calculation per configured channel range
- Added explicit val_format_endian and reg_stride for 16-bit regmap bus
- Code cleanup: alphabetical includes, ARRAY_SIZE(), unused defines
- Minor: .sign→.format field, simplify read/write order, optional hvss-supply
- Remove redundant driver documentation ad5529r.rst
- Link to v2: https://lore.kernel.org/r/20260508-ad5529r-driver-v2-0-e315441685d7@analog.com

Changes in v2:
- Fix IIO scale to use millivolts per ABI requirement
- Fix documentation voltage calculations (2.5V not 2.048V)
- Fix bipolar ranges in documentation (±5V, ±10V, ±15V, ±20V)
- Fix alphabetical ordering in documentation index
- Add missing newline to documentation file
- Fix scale units description (millivolts not microvolts)
- Include a section for driver rationale in the cover letter
- Reword contents in cover letter 12/16 bit generic->variant
- Add dependency array for spi-cpha and spi-cpol properties
- Link to v1: https://lore.kernel.org/r/20260507-ad5529r-driver-v1-0-b4460f3cb44f@analog.com

---
Janani Sunil (5):
      spi: dt-bindings: Add spi-device-addr peripheral property
      dt-bindings: iio: adc: microchip,mcp3564: Add spi-device-addr
      dt-bindings: iio: adc: microchip,mcp3911: Add spi-device-addr
      dt-bindings: iio: dac: Add AD5529R
      iio: dac: Add AD5529R DAC driver support

 .../bindings/iio/adc/microchip,mcp3564.yaml        |   9 +-
 .../bindings/iio/adc/microchip,mcp3911.yaml        |   8 +-
 .../devicetree/bindings/iio/dac/adi,ad5529r.yaml   | 224 +++++++++
 .../bindings/spi/spi-peripheral-props.yaml         |   5 +
 MAINTAINERS                                        |   8 +
 drivers/iio/dac/Kconfig                            |  17 +
 drivers/iio/dac/Makefile                           |   1 +
 drivers/iio/dac/ad5529r.c                          | 502 +++++++++++++++++++++
 8 files changed, 771 insertions(+), 3 deletions(-)
---
base-commit: 93df88612859e8e19dec93c69d563b4b73e9bd4b
change-id: 20260507-ad5529r-driver-866bbdd864de

Best regards,
-- 
Janani Sunil <janani.sunil@analog.com>

[PATCH v6 1/5] spi: dt-bindings: Add spi-device-addr peripheral property

[Janani Sunil]

Some SPI devices support sharing a single chip select across multiple
physical chips by encoding a device address in the SPI frame itself.
Add the generic spi-device-addr property for describing these hardware
addresses. The property is placed on the SPI peripheral node and may
contain multiple addresses.

Signed-off-by: Janani Sunil <janani.sunil@analog.com>
---
 Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml
index 880a9f624566..135657582131 100644
--- a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml
@@ -142,6 +142,11 @@ properties:
     minItems: 2
     maxItems: 4
 
+  spi-device-addr:
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    description:
+      Device address used when multiple peripherals share a single chip select.
+
   st,spi-midi-ns:
     deprecated: true
     description: |

-- 
2.43.0

Re: [PATCH v6 1/5] spi: dt-bindings: Add spi-device-addr peripheral property

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] The `spi-device-addr` array property groups multiple physical chips under a single Device Tree node, which violates core DT architecture and precludes describing per-chip resources.
--

--- Patch [1]: [PATCH v6 1/5] spi: dt-bindings: Add spi-device-addr peripheral property ---
commit 039a81f5133684e72f9b6f61fd5df1550f9b8b54
Author: Janani Sunil <janani.sunil@analog.com>

spi: dt-bindings: Add spi-device-addr peripheral property

This commit adds a generic spi-device-addr property to describe multiple
hardware addresses for SPI devices that share a single chip select. The
property is defined as a uint32-array to be placed on the SPI peripheral
node.

> diff --git a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml
> --- a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml
> +++ b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml

[ ... ]

> @@ -142,6 +142,11 @@ properties:
>      minItems: 2
>      maxItems: 4
>  
> +  spi-device-addr:
> +    $ref: /schemas/types.yaml#/definitions/uint32-array
> +    description:
> +      Device address used when multiple peripherals share a single chip select.

[Severity: Medium]
Does grouping multiple physical chips under a single Device Tree node using an
array property conflict with core DT architecture?

If multiple addresses are listed here, it becomes impossible to describe
distinct per-chip hardware resources, such as individual interrupts, clocks,
or power supplies for those physical chips.

Would it be more appropriate to model the shared CS as a bridge or bus node
with #address-cells = <1>, and represent each physical chip as a distinct
child node with its own reg and discrete properties? 

Since Device Tree bindings form a permanent ABI, establishing this array
pattern might permanently constrain drivers needing to represent per-chip
resources on shared chip selects.

> +
>    st,spi-midi-ns:
>      deprecated: true
>      description: |

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260715-ad5529r-driver-v6-0-cfdf8b9f5ee3@analog.com?part=1

Re: [PATCH v6 1/5] spi: dt-bindings: Add spi-device-addr peripheral property

[Mark Brown]

[-- Attachment #1: Type: text/plain, Size: 625 bytes --]

On Wed, Jul 15, 2026 at 01:41:04PM +0200, Janani Sunil wrote:
> Some SPI devices support sharing a single chip select across multiple
> physical chips by encoding a device address in the SPI frame itself.
> Add the generic spi-device-addr property for describing these hardware
> addresses. The property is placed on the SPI peripheral node and may
> contain multiple addresses.

This really isn't a generic SPI thing, if nothing else you need *far*
more information in there about how exactly this would be put onto the
bus.  If it belongs anywhere outside of the specific device's binding it
feels like it might be regmap.

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

Re: [PATCH v6 1/5] spi: dt-bindings: Add spi-device-addr peripheral property

[Nuno Sá]

On Wed, Jul 15, 2026 at 02:09:19PM +0100, Mark Brown wrote:
> On Wed, Jul 15, 2026 at 01:41:04PM +0200, Janani Sunil wrote:
> > Some SPI devices support sharing a single chip select across multiple
> > physical chips by encoding a device address in the SPI frame itself.
> > Add the generic spi-device-addr property for describing these hardware
> > addresses. The property is placed on the SPI peripheral node and may
> > contain multiple addresses.
> 
> This really isn't a generic SPI thing, if nothing else you need *far*
> more information in there about how exactly this would be put onto the
> bus.  If it belongs anywhere outside of the specific device's binding it
> feels like it might be regmap.

Just for some context,

For the analog chip, it can share the same CS line with another 3
identical chips. It has two pins that depending on how they are set act
as the device address (so only one replies to a given transfer -
naturally the peripheral driver needs to setup the correct transfer
and that depends on these pins setup and hence dt property). 

This property reflects that. Apparently some microchip chips are doing something
very similar so Conor proposed a generic property given that we would have at
least 3 users of it.

- Nuno Sá

Re: [PATCH v6 1/5] spi: dt-bindings: Add spi-device-addr peripheral property

[Mark Brown]

[-- Attachment #1: Type: text/plain, Size: 1183 bytes --]

On Wed, Jul 15, 2026 at 03:29:32PM +0200, Nuno Sá wrote:
> On Wed, Jul 15, 2026 at 02:09:19PM +0100, Mark Brown wrote:

> > This really isn't a generic SPI thing, if nothing else you need *far*
> > more information in there about how exactly this would be put onto the
> > bus.  If it belongs anywhere outside of the specific device's binding it
> > feels like it might be regmap.

> Just for some context,

> For the analog chip, it can share the same CS line with another 3
> identical chips. It has two pins that depending on how they are set act
> as the device address (so only one replies to a given transfer -
> naturally the peripheral driver needs to setup the correct transfer
> and that depends on these pins setup and hence dt property). 

> This property reflects that. Apparently some microchip chips are doing something
> very similar so Conor proposed a generic property given that we would have at
> least 3 users of it.

You still need to work out how the ID appears in the byte stream that
gets sent to/from the device, that's way more information than just a
number and not something the byte stream SPI offers is going to cope
well with.

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

[PATCH v6 2/5] dt-bindings: iio: adc: microchip,mcp3564: Add spi-device-addr

[Janani Sunil]

Add the generic spi-device-addr property to the binding and deprecate
the existing vendor specific microchip,hw-device-address property.

Signed-off-by: Janani Sunil <janani.sunil@analog.com>
---
 Documentation/devicetree/bindings/iio/adc/microchip,mcp3564.yaml | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/iio/adc/microchip,mcp3564.yaml b/Documentation/devicetree/bindings/iio/adc/microchip,mcp3564.yaml
index 675319276197..02bb198e9fa7 100644
--- a/Documentation/devicetree/bindings/iio/adc/microchip,mcp3564.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/microchip,mcp3564.yaml
@@ -80,6 +80,7 @@ properties:
     $ref: /schemas/types.yaml#/definitions/uint32
     minimum: 0
     maximum: 3
+    deprecated: true
     description:
       The address is set on a per-device basis by fuses in the factory,
       configured on request. If not requested, the fuses are set for 0x1.
@@ -91,6 +92,11 @@ properties:
       clocking of the device address (BITS[7:6] - top two bits of COMMAND BYTE
       which is first one on the wire).
 
+  spi-device-addr:
+    maxItems: 1
+    items:
+      enum: [0, 1, 2, 3]
+
   "#io-channel-cells":
     const: 1
 
@@ -123,7 +129,6 @@ dependencies:
 required:
   - compatible
   - reg
-  - microchip,hw-device-address
   - spi-max-frequency
 
 allOf:
@@ -159,7 +164,7 @@ examples:
             spi-cpha;
             spi-cpol;
             spi-max-frequency = <10000000>;
-            microchip,hw-device-address = <1>;
+            spi-device-addr = <1>;
 
             #address-cells = <1>;
             #size-cells = <0>;

-- 
2.43.0

Re: [PATCH v6 2/5] dt-bindings: iio: adc: microchip,mcp3564: Add spi-device-addr

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] The mcp3564 driver is not updated to parse the newly introduced generic `spi-device-addr` property, causing it to silently default to an incorrect address if device trees are updated to use the new property.
--

--- Patch [2]: [PATCH v6 2/5] dt-bindings: iio: adc: microchip,mcp3564: Add spi-device-addr ---
commit 63ce2b7ebde9aedefae19c7bc6bdc66fe833659e
Author: Janani Sunil <janani.sunil@analog.com>

dt-bindings: iio: adc: microchip,mcp3564: Add spi-device-addr

This commit adds the generic spi-device-addr property to the binding and
deprecates the existing vendor-specific microchip,hw-device-address property.

> diff --git a/Documentation/devicetree/bindings/iio/adc/microchip,mcp3564.yaml b/Documentation/devicetree/bindings/iio/adc/microchip,mcp3564.yaml
> index 6753192761971..02bb198e9fa73 100644
> --- a/Documentation/devicetree/bindings/iio/adc/microchip,mcp3564.yaml
> +++ b/Documentation/devicetree/bindings/iio/adc/microchip,mcp3564.yaml
[ ... ]
> @@ -91,6 +92,11 @@ properties:
>        clocking of the device address (BITS[7:6] - top two bits of COMMAND BYTE
>        which is first one on the wire).
>  
> +  spi-device-addr:
> +    maxItems: 1
> +    items:
> +      enum: [0, 1, 2, 3]
> +

[Severity: High]
Has the mcp3564 driver been updated to parse this new generic property?

If a device tree is updated to resolve the deprecation warning by replacing
microchip,hw-device-address with spi-device-addr, it looks like the driver
will fail to parse it and silently default to address 1:

drivers/iio/adc/mcp3564.c:mcp3564_config() {
    ...
    device_property_read_u32(dev, "microchip,hw-device-address", &tmp);
    ...
}

If a device uses address 0, 2, or 3, wouldn't this break SPI communication
with the ADC?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260715-ad5529r-driver-v6-0-cfdf8b9f5ee3@analog.com?part=2

[PATCH v6 3/5] dt-bindings: iio: adc: microchip,mcp3911: Add spi-device-addr

[Janani Sunil]

Add the generic spi-device-addr property to the binding and deprecate
the existing vendor specific microchip,device-addr property

Signed-off-by: Janani Sunil <janani.sunil@analog.com>
---
 Documentation/devicetree/bindings/iio/adc/microchip,mcp3911.yaml | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/iio/adc/microchip,mcp3911.yaml b/Documentation/devicetree/bindings/iio/adc/microchip,mcp3911.yaml
index 3a69ec60edb9..4a60df06bd35 100644
--- a/Documentation/devicetree/bindings/iio/adc/microchip,mcp3911.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/microchip,mcp3911.yaml
@@ -57,6 +57,12 @@ properties:
     $ref: /schemas/types.yaml#/definitions/uint32
     enum: [0, 1, 2, 3]
     default: 0
+    deprecated: true
+
+  spi-device-addr:
+    maxItems: 1
+    items:
+      enum: [0, 1, 2, 3]
 
   vref-supply:
     description: |
@@ -86,7 +92,7 @@ examples:
         interrupts = <15 2>;
         reset-gpios = <&gpio1 10 GPIO_ACTIVE_LOW>;
         spi-max-frequency = <20000000>;
-        microchip,device-addr = <0>;
+        spi-device-addr = <0>;
         vref-supply = <&vref_reg>;
         clocks = <&xtal>;
       };

-- 
2.43.0

Re: [PATCH v6 3/5] dt-bindings: iio: adc: microchip,mcp3911: Add spi-device-addr

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Medium] Driver code fails to parse the newly introduced `spi-device-addr` devicetree property.
- [Low] The `spi-device-addr` property definition omits the default fallback value that was explicitly documented for the deprecated property.
--

--- Patch [3]: [PATCH v6 3/5] dt-bindings: iio: adc: microchip,mcp3911: Add spi-device-addr ---
commit 477e23e3dcd5151c9814b58cb6b94b490d963f05
Author: Janani Sunil <janani.sunil@analog.com>

dt-bindings: iio: adc: microchip,mcp3911: Add spi-device-addr

This commit adds the generic spi-device-addr property to the binding
schema and marks the vendor-specific microchip,device-addr property
as deprecated.

> diff --git a/Documentation/devicetree/bindings/iio/adc/microchip,mcp3911.yaml b/Documentation/devicetree/bindings/iio/adc/microchip,mcp3911.yaml
> index 3a69ec60edb91..4a60df06bd357 100644
> --- a/Documentation/devicetree/bindings/iio/adc/microchip,mcp3911.yaml
> +++ b/Documentation/devicetree/bindings/iio/adc/microchip,mcp3911.yaml
> @@ -57,6 +57,12 @@ properties:
>      $ref: /schemas/types.yaml#/definitions/uint32
>      enum: [0, 1, 2, 3]
>      default: 0
> +    deprecated: true
> +
> +  spi-device-addr:
> +    maxItems: 1
> +    items:
> +      enum: [0, 1, 2, 3]

[Severity: Low]
Is it intentional to omit the default fallback value here?

The deprecated property explicitly documents a default value of 0, but this
new definition omits it. This causes the schema to lose information about
the fallback behavior when the address property is omitted. Should it
include default: [0]?

[ ... ]

> @@ -86,7 +92,7 @@ examples:
>          interrupts = <15 2>;
>          reset-gpios = <&gpio1 10 GPIO_ACTIVE_LOW>;
>          spi-max-frequency = <20000000>;
> -        microchip,device-addr = <0>;
> +        spi-device-addr = <0>;

[Severity: Medium]
Will the driver fail to communicate with the hardware if a device tree uses
this newly recommended property?

The devicetree example explicitly advertises the new spi-device-addr
property, but looking at drivers/iio/adc/mcp3911.c:mcp3911_probe(), the
driver only attempts to read the older properties:

	ret = device_property_read_u32(dev, "microchip,device-addr", &adc->dev_addr);
	if (ret)
		device_property_read_u32(dev, "device-addr", &adc->dev_addr);

Similarly, in drivers/iio/adc/mcp3564.c:mcp3564_config(), the driver only
attempts to read the deprecated vendor property:

	device_property_read_u32(dev, "microchip,hw-device-address", &tmp);

Because the driver code does not parse spi-device-addr, it seems it will
silently fall back to the default address if a device tree provides the
new property instead of the deprecated ones.

>          vref-supply = <&vref_reg>;
>          clocks = <&xtal>;
>        };

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260715-ad5529r-driver-v6-0-cfdf8b9f5ee3@analog.com?part=3

[PATCH v6 4/5] dt-bindings: iio: dac: Add AD5529R

[Janani Sunil]

Devicetree bindings for AD5529R 16 channel 12/16 bit high voltage,
buffered voltage output digital-to-analog converter (DAC) with an
integrated precision reference.

Signed-off-by: Janani Sunil <janani.sunil@analog.com>
---
 .../devicetree/bindings/iio/dac/adi,ad5529r.yaml   | 224 +++++++++++++++++++++
 MAINTAINERS                                        |   7 +
 2 files changed, 231 insertions(+)

diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5529r.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5529r.yaml
new file mode 100644
index 000000000000..730206fd6eab
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5529r.yaml
@@ -0,0 +1,224 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/dac/adi,ad5529r.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Analog Devices AD5529R 16-Channel 12/16-bit High Voltage DAC
+
+maintainers:
+  - Janani Sunil <janani.sunil@analog.com>
+
+description: |
+  The AD5529R is a 16-channel, 12-bit or 16-bit, high voltage, buffered voltage
+  output digital-to-analog converter (DAC) with an integrated precision reference.
+  The device operates from unipolar and bipolar supplies. It is guaranteed
+  monotonic and has built-in rail-to-rail output buffers that can source or
+  sink up to 25mA.
+
+  Specifications:
+  * 16 independent 12-bit or 16-bit DAC channels
+  * Independently programmable output ranges: 0V to 5V, 0V to 10V, 0V to 20V,
+    0V to 40V, ±5V, ±10V, ±15V, and ±20V
+  * The device supports SPI communication with Mode 0 and Mode 3.
+  * 4.096V precision reference, 12ppm/°C maximum
+  * Built-in function generation: Toggle, Sinusoidal Dither, and Ramp waveforms
+  * Multiplexer for output voltage, load current sense and die temperature
+
+  Datasheet: https://www.analog.com/media/en/technical-documentation/data-sheets/ad5529r.pdf
+
+properties:
+  compatible:
+    enum:
+      - adi,ad5529r-16   # 16-bit variant
+      - adi,ad5529r-12   # 12-bit variant
+
+  reg:
+    maxItems: 1
+
+  spi-max-frequency:
+    maximum: 25000000
+    description:
+      Maximum SPI frequency. The device supports SPI Mode 0 and Mode 3.
+      Read operations are limited to 25MHz maximum.
+
+  reset-gpios:
+    maxItems: 1
+    description:
+      GPIO connected to the RESET pin. Active low. When asserted low,
+      performs a power-on reset and initializes the device to its default state.
+
+  clear-gpios:
+    maxItems: 1
+    description:
+      GPIO connected to the CLEAR pin. Active low. When asserted low,
+      clears all DAC data registers without affecting configuration settings.
+
+  interrupts:
+    maxItems: 1
+    description:
+      Interrupt connected to the ALARM pin. Active low interrupt output
+      for overtemperature conditions, SPI CRC errors, and function completion.
+
+  pwms:
+    minItems: 1
+    maxItems: 4
+    description:
+      PWM signals connected to the TG0-TG3 toggle pins. Pulsing these pins
+      based on trigger edge settings allows selected DACs to be updated
+      synchronously for digital function generation.
+
+  pwm-names:
+    minItems: 1
+    maxItems: 4
+    items:
+      enum: [ tg0, tg1, tg2, tg3 ]
+
+  io-channels:
+    maxItems: 1
+    description:
+      ADC channel connected to the MUXOUT pin for monitoring output voltage,
+      load current sense, and die temperature.
+
+  io-channel-names:
+    const: muxout
+
+  vdd-supply:
+    description: Digital power supply (1.08V to 1.98V)
+
+  avdd-supply:
+    description: Analog power supply (4.75V to 5.25V)
+
+  hvdd-supply:
+    description:
+      High voltage positive supply (7V to 45V). Supply voltage should be chosen
+      based on configured output ranges (see datasheet Table 9).
+
+  hvss-supply:
+    description:
+      High voltage negative supply (-22.5V to 0V). Required only when using
+      bipolar output ranges (±5V, ±10V, ±15V, ±20V). Supply voltage should be
+      chosen based on configured output ranges (see datasheet Table 9).
+
+  vref-supply:
+    description:
+      External voltage reference supply (4.056V to 4.136V, typically 4.096V).
+      When specified, the device uses external reference mode and the VREF pin
+      becomes an input. The device uses the internal 4.096V precision reference
+      otherwise.
+
+  spi-device-addr:
+    minItems: 1
+    maxItems: 4
+    items:
+      enum: [0, 1, 2, 3]
+    default: [0]
+    description:
+      Hardware address of each device, selected by the ID0 and ID1 pins.
+      Up to four AD5529R devices can share a single SPI chip select.
+
+  "#address-cells":
+    const: 1
+
+  "#size-cells":
+    const: 0
+
+patternProperties:
+  "^channel@([0-9a-f]{1,2})$":
+    $ref: dac.yaml
+    type: object
+    description: Child nodes for individual channel configuration
+
+    properties:
+      reg:
+        description:
+          Flattened channel number across all AD5529R devices sharing the chip
+          select. Within each 16-channel block, the physical channel number is reg % 16.
+        minimum: 0
+        maximum: 63
+
+      output-range-microvolt:
+        description:
+          Output voltage range for this channel as [min, max] in
+          microvolts.
+        oneOf:
+          - items:
+              - const: 0
+                default: 0
+              - enum: [5000000, 10000000, 20000000, 40000000]
+                default: 5000000
+          - items:
+              - const: -5000000
+              - const: 5000000
+          - items:
+              - const: -10000000
+              - const: 10000000
+          - items:
+              - const: -15000000
+              - const: 15000000
+          - items:
+              - const: -20000000
+              - const: 20000000
+
+    required:
+      - reg
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - vdd-supply
+  - avdd-supply
+  - hvdd-supply
+
+dependencies:
+  spi-cpha: [ spi-cpol ]
+  spi-cpol: [ spi-cpha ]
+
+allOf:
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        dac@0 {
+            compatible = "adi,ad5529r-16";
+            reg = <0>;
+            spi-max-frequency = <25000000>;
+            spi-device-addr = <0>;
+
+            vdd-supply = <&vdd_regulator>;
+            avdd-supply = <&avdd_regulator>;
+            hvdd-supply = <&hvdd_regulator>;
+            hvss-supply = <&hvss_regulator>;
+
+            reset-gpios = <&gpio0 87 GPIO_ACTIVE_LOW>;
+
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            channel@0 {
+                reg = <0>;
+                output-range-microvolt = <0 5000000>;
+            };
+
+            channel@1 {
+                reg = <1>;
+                output-range-microvolt = <(-10000000) 10000000>;
+            };
+
+            channel@2 {
+                reg = <2>;
+                output-range-microvolt = <0 40000000>;
+            };
+        };
+    };
+...
diff --git a/MAINTAINERS b/MAINTAINERS
index d6c3c7d22403..320e84765ce6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1507,6 +1507,13 @@ W:	https://ez.analog.com/linux-software-drivers
 F:	Documentation/devicetree/bindings/iio/adc/adi,ad4851.yaml
 F:	drivers/iio/adc/ad4851.c
 
+ANALOG DEVICES INC AD5529R DRIVER
+M:	Janani Sunil <janani.sunil@analog.com>
+L:	linux-iio@vger.kernel.org
+S:	Supported
+W:	https://ez.analog.com/linux-software-drivers
+F:	Documentation/devicetree/bindings/iio/dac/adi,ad5529r.yaml
+
 ANALOG DEVICES INC AD5706R DRIVER
 M:	Alexis Czezar Torreno <alexisczezar.torreno@analog.com>
 L:	linux-iio@vger.kernel.org

-- 
2.43.0

Re: [PATCH v6 4/5] dt-bindings: iio: dac: Add AD5529R

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Medium] Missing `spi-cpha` and `spi-cpol` in the `properties` block causes valid SPI Mode 3 configurations to fail dt-schema validation.
- [Medium] Using `additionalProperties: false` with `$ref: dac.yaml` breaks inheritance, causing standard DAC properties to be incorrectly rejected.
--

--- Patch [4]: [PATCH v6 4/5] dt-bindings: iio: dac: Add AD5529R ---
commit e027ded7c4d70f1636e16dc892937b3656b0c91d
Author: Janani Sunil <janani.sunil@analog.com>

dt-bindings: iio: dac: Add AD5529R

Devicetree bindings for AD5529R 16 channel 12/16 bit high voltage,
buffered voltage output digital-to-analog converter (DAC) with an
integrated precision reference.

> diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5529r.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5529r.yaml
> new file mode 100644
> index 0000000000000..730206fd6eaba
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5529r.yaml
> @@ -0,0 +1,224 @@

[ ... ]

> +patternProperties:
> +  "^channel@([0-9a-f]{1,2})$":
> +    $ref: dac.yaml
> +    type: object
> +    description: Child nodes for individual channel configuration
> +
> +    properties:
> +      reg:
> +        description:
> +          Flattened channel number across all AD5529R devices sharing the chip
> +          select. Within each 16-channel block, the physical channel number is reg % 16.
> +        minimum: 0
> +        maximum: 63
> +
> +      output-range-microvolt:

[ ... ]

> +    required:
> +      - reg
> +
> +    additionalProperties: false

[Severity: Medium]
Since this node uses $ref: dac.yaml, shouldn't this be
unevaluatedProperties: false instead?

Using additionalProperties: false restricts valid properties strictly to the
local properties block. Standard DAC properties inherited from dac.yaml
(such as label) will be incorrectly rejected by dt_binding_check.

> +
> +required:
> +  - compatible
> +  - reg
> +  - vdd-supply
> +  - avdd-supply
> +  - hvdd-supply
> +
> +dependencies:
> +  spi-cpha: [ spi-cpol ]
> +  spi-cpol: [ spi-cpha ]

[Severity: Medium]
Will this fail dt_binding_check validation for valid SPI Mode 3
configurations?

The dependencies block enforces that both properties are present, but spi-cpha
and spi-cpol are not explicitly defined in the properties block.

Because unevaluatedProperties: false is used at the top level and
spi-peripheral-props.yaml does not define spi-cpha or spi-cpol, they must be
explicitly declared (e.g., spi-cpha: true) in the properties block.

Otherwise, configurations correctly using SPI Mode 3 will be rejected with an
"unevaluated property" error.

> +
> +allOf:
> +  - $ref: /schemas/spi/spi-peripheral-props.yaml#
> +
> +unevaluatedProperties: false

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260715-ad5529r-driver-v6-0-cfdf8b9f5ee3@analog.com?part=4

[PATCH v6 5/5] iio: dac: Add AD5529R DAC driver support

[Janani Sunil]

Add support for AD5529R 16-channel, 12/16 bit Digital to Analog Converter
from Analog Devices.

The device communicates over SPI and supports per-channel output range
configuration. An optional external 4.096V reference can be used in
place of the internal reference.

Signed-off-by: Janani Sunil <janani.sunil@analog.com>
---
 MAINTAINERS               |   1 +
 drivers/iio/dac/Kconfig   |  17 ++
 drivers/iio/dac/Makefile  |   1 +
 drivers/iio/dac/ad5529r.c | 502 ++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 521 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 320e84765ce6..143714e27d51 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1513,6 +1513,7 @@ L:	linux-iio@vger.kernel.org
 S:	Supported
 W:	https://ez.analog.com/linux-software-drivers
 F:	Documentation/devicetree/bindings/iio/dac/adi,ad5529r.yaml
+F:	drivers/iio/dac/ad5529r.c
 
 ANALOG DEVICES INC AD5706R DRIVER
 M:	Alexis Czezar Torreno <alexisczezar.torreno@analog.com>
diff --git a/drivers/iio/dac/Kconfig b/drivers/iio/dac/Kconfig
index 657c68e75542..bb1d59889a2a 100644
--- a/drivers/iio/dac/Kconfig
+++ b/drivers/iio/dac/Kconfig
@@ -134,6 +134,23 @@ config AD5449
 	  To compile this driver as a module, choose M here: the
 	  module will be called ad5449.
 
+config AD5529R
+	tristate "Analog Devices AD5529R High Voltage DAC driver"
+	depends on SPI_MASTER
+	select REGMAP_SPI
+	help
+	  Say yes here to build support for Analog Devices AD5529R
+	  16-Channel, 12-Bit/16-Bit, 40V High Voltage Precision Digital to Analog
+	  Converter.
+
+	  The device features multiple output voltage ranges from -20V to +20V,
+	  built-in 4.096V voltage reference, and digital functions including
+	  toggle, dither, and ramp modes. Supports both 12-bit and 16-bit
+	  resolution variants.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called ad5529r.
+
 config AD5592R_BASE
 	tristate
 
diff --git a/drivers/iio/dac/Makefile b/drivers/iio/dac/Makefile
index 003431798498..f35e060b3643 100644
--- a/drivers/iio/dac/Makefile
+++ b/drivers/iio/dac/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_AD5446) += ad5446.o
 obj-$(CONFIG_AD5446_SPI) += ad5446-spi.o
 obj-$(CONFIG_AD5446_I2C) += ad5446-i2c.o
 obj-$(CONFIG_AD5449) += ad5449.o
+obj-$(CONFIG_AD5529R) += ad5529r.o
 obj-$(CONFIG_AD5592R_BASE) += ad5592r-base.o
 obj-$(CONFIG_AD5592R) += ad5592r.o
 obj-$(CONFIG_AD5593R) += ad5593r.o
diff --git a/drivers/iio/dac/ad5529r.c b/drivers/iio/dac/ad5529r.c
new file mode 100644
index 000000000000..c279dc530d68
--- /dev/null
+++ b/drivers/iio/dac/ad5529r.c
@@ -0,0 +1,502 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AD5529R Digital-to-Analog Converter Driver
+ * 16-Channel, 12/16-Bit, 40V High Voltage Precision DAC
+ *
+ * Copyright 2026 Analog Devices Inc.
+ * Author: Janani Sunil <janani.sunil@analog.com>
+ */
+
+#include <linux/array_size.h>
+#include <linux/bits.h>
+#include <linux/delay.h>
+#include <linux/dev_printk.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/iio/iio.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/property.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/reset.h>
+#include <linux/spi/spi.h>
+#include <linux/types.h>
+#include <linux/units.h>
+
+#define AD5529R_REG_INTERFACE_CONFIG_A		0x00
+#define   AD5529R_INTERFACE_CONFIG_A_SW_RESET	(BIT(7) | BIT(0))
+#define   AD5529R_INTERFACE_CONFIG_A_ADDR_ASCENSION	BIT(5)
+#define   AD5529R_INTERFACE_CONFIG_A_SDO_ENABLE	BIT(4)
+#define AD5529R_REG_DEVICE_CONFIG		0x02
+#define AD5529R_REG_CHIP_GRADE			0x06
+#define AD5529R_REG_SCRATCH_PAD			0x0A
+#define AD5529R_REG_SPI_REVISION		0x0B
+#define AD5529R_REG_VENDOR_H			0x0D
+#define AD5529R_REG_STREAM_MODE			0x0E
+#define AD5529R_REG_INTERFACE_STATUS_A		0x11
+#define AD5529R_REG_MULTI_DAC_CH_SEL		0x14
+#define AD5529R_REG_OUT_RANGE_BASE		0x3C
+#define AD5529R_REG_OUT_RANGE(ch)		(AD5529R_REG_OUT_RANGE_BASE + (ch) * 2)
+#define AD5529R_REG_DAC_INPUT_A_BASE		0x148
+#define AD5529R_REG_DAC_INPUT_A(ch)		(AD5529R_REG_DAC_INPUT_A_BASE + (ch) * 2)
+#define AD5529R_REG_DAC_DATA_READBACK_BASE	0x16A
+#define AD5529R_REG_TSENS_ALERT_FLAG		0x18C
+#define AD5529R_REG_TSENS_SHTD_FLAG		0x18E
+#define AD5529R_REG_FUNC_BUSY			0x1A0
+#define AD5529R_REG_REF_SEL			0x1A2
+#define   AD5529R_REF_SEL_INTERNAL_REF		BIT(0)
+#define AD5529R_REG_INIT_CRC_ERR_STAT		0x1A4
+#define AD5529R_REG_MULTI_DAC_HOTPATH_SW_LDAC	0x1A8
+
+#define AD5529R_MAX_REGISTER			0x232
+#define AD5529R_8BIT_REG_MAX			0x13
+#define AD5529R_SPI_READ_FLAG			0x80
+#define AD5529R_ADDR_SHIFT			12
+
+struct ad5529r_model_data {
+	const char *model_name;
+	unsigned int resolution;
+};
+
+#define AD5529R_DAC_CHANNEL(chan) ((struct iio_chan_spec) {		\
+	.type = IIO_VOLTAGE,						\
+	.indexed = 1,							\
+	.output = 1,							\
+	.channel = (chan),						\
+	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |			\
+			      BIT(IIO_CHAN_INFO_SCALE) |		\
+			      BIT(IIO_CHAN_INFO_OFFSET),		\
+})
+
+static const char * const ad5529r_supply_names[] = {
+	"vdd",
+	"avdd",
+	"hvdd",
+};
+
+static const struct ad5529r_model_data ad5529r_16bit_model_data = {
+	.model_name = "ad5529r-16",
+	.resolution = 16,
+};
+
+static const struct ad5529r_model_data ad5529r_12bit_model_data = {
+	.model_name = "ad5529r-12",
+	.resolution = 12,
+};
+
+enum ad5529r_output_range {
+	AD5529R_RANGE_0V_5V,
+	AD5529R_RANGE_0V_10V,
+	AD5529R_RANGE_0V_20V,
+	AD5529R_RANGE_0V_40V,
+	AD5529R_RANGE_NEG5V_5V,
+	AD5529R_RANGE_NEG10V_10V,
+	AD5529R_RANGE_NEG15V_15V,
+	AD5529R_RANGE_NEG20V_20V,
+};
+
+static const s32 ad5529r_output_ranges_mV[8][2] = {
+	[AD5529R_RANGE_0V_5V] = { 0, 5000 },
+	[AD5529R_RANGE_0V_10V] = { 0, 10000 },
+	[AD5529R_RANGE_0V_20V] = { 0, 20000 },
+	[AD5529R_RANGE_0V_40V] = { 0, 40000 },
+	[AD5529R_RANGE_NEG5V_5V] = { -5000, 5000 },
+	[AD5529R_RANGE_NEG10V_10V] = { -10000, 10000 },
+	[AD5529R_RANGE_NEG15V_15V] = { -15000, 15000 },
+	[AD5529R_RANGE_NEG20V_20V] = { -20000, 20000 },
+};
+
+struct ad5529r_state {
+	struct spi_device *spi;
+	const struct ad5529r_model_data *model_data;
+	struct regmap *regmap_8bit;
+	struct regmap *regmap_16bit;
+	struct iio_chan_spec channels[16];
+	unsigned int num_channels;
+	enum ad5529r_output_range output_range_idx[16];
+};
+
+static const struct regmap_range ad5529r_8bit_readable_ranges[] = {
+	regmap_reg_range(AD5529R_REG_INTERFACE_CONFIG_A, AD5529R_REG_CHIP_GRADE),
+	regmap_reg_range(AD5529R_REG_SCRATCH_PAD, AD5529R_REG_VENDOR_H),
+	regmap_reg_range(AD5529R_REG_STREAM_MODE, AD5529R_REG_INTERFACE_STATUS_A),
+};
+
+static const struct regmap_range ad5529r_16bit_readable_ranges[] = {
+	regmap_reg_range(AD5529R_REG_MULTI_DAC_CH_SEL, AD5529R_REG_INIT_CRC_ERR_STAT),
+	regmap_reg_range(AD5529R_REG_MULTI_DAC_HOTPATH_SW_LDAC, AD5529R_MAX_REGISTER),
+};
+
+static const struct regmap_access_table ad5529r_8bit_readable_table = {
+	.yes_ranges = ad5529r_8bit_readable_ranges,
+	.n_yes_ranges = ARRAY_SIZE(ad5529r_8bit_readable_ranges),
+};
+
+static const struct regmap_access_table ad5529r_16bit_readable_table = {
+	.yes_ranges = ad5529r_16bit_readable_ranges,
+	.n_yes_ranges = ARRAY_SIZE(ad5529r_16bit_readable_ranges),
+};
+
+static const struct regmap_range ad5529r_8bit_read_only_ranges[] = {
+	regmap_reg_range(AD5529R_REG_DEVICE_CONFIG, AD5529R_REG_CHIP_GRADE),
+	regmap_reg_range(AD5529R_REG_SPI_REVISION, AD5529R_REG_VENDOR_H),
+};
+
+static const struct regmap_range ad5529r_16bit_read_only_ranges[] = {
+	regmap_reg_range(AD5529R_REG_DAC_DATA_READBACK_BASE,
+			 AD5529R_REG_DAC_DATA_READBACK_BASE + 15 * 2),
+	regmap_reg_range(AD5529R_REG_TSENS_ALERT_FLAG, AD5529R_REG_TSENS_SHTD_FLAG),
+	regmap_reg_range(AD5529R_REG_FUNC_BUSY, AD5529R_REG_FUNC_BUSY),
+	regmap_reg_range(AD5529R_REG_INIT_CRC_ERR_STAT, AD5529R_REG_INIT_CRC_ERR_STAT),
+};
+
+static const struct regmap_access_table ad5529r_8bit_writeable_table = {
+	.no_ranges = ad5529r_8bit_read_only_ranges,
+	.n_no_ranges = ARRAY_SIZE(ad5529r_8bit_read_only_ranges),
+};
+
+static const struct regmap_access_table ad5529r_16bit_writeable_table = {
+	.no_ranges = ad5529r_16bit_read_only_ranges,
+	.n_no_ranges = ARRAY_SIZE(ad5529r_16bit_read_only_ranges),
+};
+
+static const struct regmap_config ad5529r_regmap_8bit_config = {
+	.name = "ad5529r-8bit",
+	.reg_bits = 16,
+	.val_bits = 8,
+	.max_register = AD5529R_8BIT_REG_MAX,
+	.read_flag_mask = AD5529R_SPI_READ_FLAG,
+	.rd_table = &ad5529r_8bit_readable_table,
+	.wr_table = &ad5529r_8bit_writeable_table,
+};
+
+static const struct regmap_config ad5529r_regmap_16bit_config = {
+	.name = "ad5529r-16bit",
+	.reg_bits = 16,
+	.val_bits = 16,
+	.max_register = AD5529R_MAX_REGISTER,
+	.read_flag_mask = AD5529R_SPI_READ_FLAG,
+	.val_format_endian = REGMAP_ENDIAN_LITTLE,
+	.rd_table = &ad5529r_16bit_readable_table,
+	.wr_table = &ad5529r_16bit_writeable_table,
+	.reg_stride = 2,
+};
+
+static struct regmap *ad5529r_get_regmap(struct ad5529r_state *st,
+					 unsigned int reg)
+{
+	if (reg <= AD5529R_8BIT_REG_MAX)
+		return st->regmap_8bit;
+
+	return st->regmap_16bit;
+}
+
+static int ad5529r_reset(struct ad5529r_state *st)
+{
+	struct reset_control *rst;
+	int ret;
+
+	rst = devm_reset_control_get_optional_exclusive(&st->spi->dev, NULL);
+	if (IS_ERR(rst))
+		return PTR_ERR(rst);
+
+	if (rst) {
+		ret = reset_control_assert(rst);
+		if (ret)
+			return ret;
+
+		ret = reset_control_deassert(rst);
+		if (ret)
+			return ret;
+	} else {
+		ret = regmap_write(st->regmap_8bit, AD5529R_REG_INTERFACE_CONFIG_A,
+				   AD5529R_INTERFACE_CONFIG_A_SW_RESET);
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * Wait 10 ms for digital initialization to complete.
+	 * Per datasheet, Interface Status A register NOT_READY_ERR bit is
+	 * set if SPI transactions are attempted before digital initialization
+	 * completes.
+	 */
+	fsleep(10 * USEC_PER_MSEC);
+
+	return regmap_write(st->regmap_8bit, AD5529R_REG_INTERFACE_CONFIG_A,
+			    AD5529R_INTERFACE_CONFIG_A_SDO_ENABLE |
+			    AD5529R_INTERFACE_CONFIG_A_ADDR_ASCENSION);
+}
+
+static int ad5529r_read_raw(struct iio_dev *indio_dev,
+			    struct iio_chan_spec const *chan,
+			    int *val, int *val2, long mask)
+{
+	struct ad5529r_state *st = iio_priv(indio_dev);
+	unsigned int reg_addr, reg_val_h;
+	int ret, range_idx, span_mv;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		/*
+		 * Read from DAC_INPUT_A register rather than DAC_DATA_READBACK.
+		 * The DAC operates in transparent mode and directly reflects
+		 * whatever value is written to the INPUT_A register.
+		 */
+		reg_addr = AD5529R_REG_DAC_INPUT_A(chan->channel);
+		ret = regmap_read(st->regmap_16bit, reg_addr, &reg_val_h);
+		if (ret)
+			return ret;
+
+		*val = reg_val_h;
+
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		range_idx = st->output_range_idx[chan->channel];
+
+		span_mv = ad5529r_output_ranges_mV[range_idx][1] -
+			  ad5529r_output_ranges_mV[range_idx][0];
+		*val = span_mv;
+		*val2 = st->model_data->resolution;
+
+		return IIO_VAL_FRACTIONAL_LOG2;
+	case IIO_CHAN_INFO_OFFSET:
+		range_idx = st->output_range_idx[chan->channel];
+
+		if (ad5529r_output_ranges_mV[range_idx][0] < 0)
+			*val = -(1 << (st->model_data->resolution - 1));
+		else
+			*val = 0;
+
+		return IIO_VAL_INT;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int ad5529r_write_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan,
+			     int val, int val2, long mask)
+{
+	struct ad5529r_state *st = iio_priv(indio_dev);
+	unsigned int reg_addr;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		if (val < 0 || val > GENMASK(st->model_data->resolution - 1, 0))
+			return -EINVAL;
+
+		reg_addr = AD5529R_REG_DAC_INPUT_A(chan->channel);
+
+		return regmap_write(st->regmap_16bit, reg_addr, val);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int ad5529r_find_output_range(const s32 *vals)
+{
+	for (unsigned int i = 0; i < ARRAY_SIZE(ad5529r_output_ranges_mV); i++) {
+		const s32 *range = ad5529r_output_ranges_mV[i];
+
+		if (vals[0] == range[0] * (MICRO / MILLI) &&
+		    vals[1] == range[1] * (MICRO / MILLI))
+			return i;
+	}
+
+	return -EINVAL;
+}
+
+static int ad5529r_parse_channel_ranges(struct device *dev,
+					struct ad5529r_state *st)
+{
+	s32 vals[2];
+	int ret, range_idx;
+	u32 ch;
+
+	device_for_each_child_node_scoped(dev, child) {
+		ret = fwnode_property_read_u32(child, "reg", &ch);
+		if (ret)
+			return dev_err_probe(dev, ret,
+					     "Missing reg property in channel node\n");
+
+		if (ch >= 16)
+			return dev_err_probe(dev, -EINVAL,
+					     "Channel %u exceeds maximum 15\n",
+					     ch);
+
+		if (fwnode_property_present(child, "output-range-microvolt")) {
+			/*
+			 * DT stores cells as raw 32-bit values; signed endpoints are
+			 * encoded by dtc in two's-complement and then interpreted
+			 * here as s32.
+			 */
+			ret = fwnode_property_read_u32_array(child,
+							     "output-range-microvolt",
+							     (u32 *)vals, ARRAY_SIZE(vals));
+			if (ret < 0)
+				return dev_err_probe(dev, ret,
+						     "Failed to read range for ch %u\n",
+						     ch);
+
+			range_idx = ad5529r_find_output_range(vals);
+			if (range_idx < 0)
+				return dev_err_probe(dev, range_idx,
+						     "Invalid range [%d %d] for ch %u\n",
+						     vals[0], vals[1], ch);
+		} else {
+			range_idx = AD5529R_RANGE_0V_5V;
+		}
+
+		st->output_range_idx[ch] = range_idx;
+		ret = regmap_write(st->regmap_16bit,
+				   AD5529R_REG_OUT_RANGE(ch), range_idx);
+		if (ret)
+			return dev_err_probe(dev, ret,
+					     "Failed to configure range for ch %u\n",
+					     ch);
+
+		st->channels[st->num_channels++] = AD5529R_DAC_CHANNEL(ch);
+	}
+
+	return 0;
+}
+
+static int ad5529r_reg_access(struct iio_dev *indio_dev,
+			      unsigned int reg,
+			      unsigned int writeval,
+			      unsigned int *readval)
+{
+	struct ad5529r_state *st = iio_priv(indio_dev);
+
+	if (readval)
+		return regmap_read(ad5529r_get_regmap(st, reg), reg, readval);
+
+	return regmap_write(ad5529r_get_regmap(st, reg), reg, writeval);
+}
+
+static const struct iio_info ad5529r_info = {
+	.read_raw = ad5529r_read_raw,
+	.write_raw = ad5529r_write_raw,
+	.debugfs_reg_access = ad5529r_reg_access,
+};
+
+static int ad5529r_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct iio_dev *indio_dev;
+	struct ad5529r_state *st;
+	struct regmap_config regmap_8bit_cfg = ad5529r_regmap_8bit_config;
+	struct regmap_config regmap_16bit_cfg = ad5529r_regmap_16bit_config;
+	bool external_vref;
+	u32 dev_addr = 0;
+	int ret;
+
+	indio_dev = devm_iio_device_alloc(dev, sizeof(*st));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	st = iio_priv(indio_dev);
+
+	st->spi = spi;
+
+	st->model_data = spi_get_device_match_data(spi);
+	if (!st->model_data)
+		return dev_err_probe(dev, -EINVAL,
+				     "Failed to identify device variant\n");
+
+	device_property_read_u32(dev, "spi-device-addr", &dev_addr);
+	if (dev_addr > 3)
+		return dev_err_probe(dev, -EINVAL,
+				     "spi-device-addr %u out of range [0, 3]\n",
+				     dev_addr);
+	regmap_8bit_cfg.reg_base = dev_addr << AD5529R_ADDR_SHIFT;
+	regmap_16bit_cfg.reg_base = dev_addr << AD5529R_ADDR_SHIFT;
+
+	ret = devm_regulator_bulk_get_enable(dev, ARRAY_SIZE(ad5529r_supply_names),
+					     ad5529r_supply_names);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "Failed to get and enable regulators\n");
+
+	ret = devm_regulator_get_enable_optional(dev, "hvss");
+	if (ret && ret != -ENODEV)
+		return dev_err_probe(dev, ret,
+				     "Failed to get and enable hvss regulator\n");
+
+	ret = devm_regulator_get_enable_optional(dev, "vref");
+	if (ret == -ENODEV)
+		external_vref = false;
+	else if (!ret)
+		external_vref = true;
+	else
+		return dev_err_probe(dev, ret,
+				     "Failed to get and enable vref regulator\n");
+
+	st->regmap_8bit = devm_regmap_init_spi(spi, &regmap_8bit_cfg);
+	if (IS_ERR(st->regmap_8bit))
+		return dev_err_probe(dev, PTR_ERR(st->regmap_8bit),
+				     "Failed to initialize 8-bit regmap\n");
+
+	st->regmap_16bit = devm_regmap_init_spi(spi, &regmap_16bit_cfg);
+	if (IS_ERR(st->regmap_16bit))
+		return dev_err_probe(dev, PTR_ERR(st->regmap_16bit),
+				     "Failed to initialize 16-bit regmap\n");
+
+	ret = ad5529r_reset(st);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to reset device\n");
+
+	ret = regmap_assign_bits(st->regmap_16bit, AD5529R_REG_REF_SEL,
+				 AD5529R_REF_SEL_INTERNAL_REF,
+				 external_vref ? 0 : AD5529R_REF_SEL_INTERNAL_REF);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to configure reference\n");
+
+	ret = ad5529r_parse_channel_ranges(dev, st);
+	if (ret)
+		return ret;
+
+	indio_dev->name = st->model_data->model_name;
+	indio_dev->info = &ad5529r_info;
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->channels = st->channels;
+	indio_dev->num_channels = st->num_channels;
+
+	return devm_iio_device_register(dev, indio_dev);
+}
+
+static const struct of_device_id ad5529r_of_match[] = {
+	{ .compatible = "adi,ad5529r-16", .data = &ad5529r_16bit_model_data },
+	{ .compatible = "adi,ad5529r-12", .data = &ad5529r_12bit_model_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ad5529r_of_match);
+
+static const struct spi_device_id ad5529r_id[] = {
+	{
+		.name = "ad5529r-16",
+		.driver_data = (kernel_ulong_t)&ad5529r_16bit_model_data,
+	},
+	{
+		.name = "ad5529r-12",
+		.driver_data = (kernel_ulong_t)&ad5529r_12bit_model_data,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, ad5529r_id);
+
+static struct spi_driver ad5529r_driver = {
+	.driver = {
+		.name = "ad5529r",
+		.of_match_table = ad5529r_of_match,
+	},
+	.probe = ad5529r_probe,
+	.id_table = ad5529r_id,
+};
+module_spi_driver(ad5529r_driver);
+
+MODULE_AUTHOR("Janani Sunil <janani.sunil@analog.com>");
+MODULE_DESCRIPTION("Analog Devices AD5529R 12/16-bit DAC driver");
+MODULE_LICENSE("GPL");

-- 
2.43.0

Re: [PATCH v6 5/5] iio: dac: Add AD5529R DAC driver support

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 5 potential issue(s) to consider:
- [High] Heap buffer overflow during device tree channel parsing
- [High] Incorrect Regmap endianness configuration corrupts SPI communication
- [Medium] Incorrect regulator presence detection when CONFIG_REGULATOR=n
- [Medium] Missing timing delay between hardware reset assert and deassert
- [Medium] Potential data misalignment for 12-bit device variant
--

--- Patch [5]: [PATCH v6 5/5] iio: dac: Add AD5529R DAC driver support ---
commit e8333f8884287977f99dcd3fe867d9426fc20f71
Author: Janani Sunil <janani.sunil@analog.com>

iio: dac: Add AD5529R DAC driver support

Add support for AD5529R 16-channel, 12/16 bit Digital to Analog Converter
from Analog Devices.

> diff --git a/drivers/iio/dac/ad5529r.c b/drivers/iio/dac/ad5529r.c
> new file mode 100644
> index 0000000000000..c279dc530d688
> --- /dev/null
> +++ b/drivers/iio/dac/ad5529r.c
> @@ -0,0 +1,502 @@

[ ... ]

> +static const struct regmap_config ad5529r_regmap_16bit_config = {
> +	.name = "ad5529r-16bit",
> +	.reg_bits = 16,
> +	.val_bits = 16,
> +	.max_register = AD5529R_MAX_REGISTER,
> +	.read_flag_mask = AD5529R_SPI_READ_FLAG,
> +	.val_format_endian = REGMAP_ENDIAN_LITTLE,

[Severity: High]
Is this Little Endian configuration correct? Analog Devices SPI peripherals 
typically use Big Endian (MSB first) for 16-bit payloads. Could this 
byte-swap and corrupt the SPI data on transmission?

> +	.rd_table = &ad5529r_16bit_readable_table,
> +	.wr_table = &ad5529r_16bit_writeable_table,
> +	.reg_stride = 2,
> +};

[ ... ]

> +static int ad5529r_reset(struct ad5529r_state *st)
> +{
> +	struct reset_control *rst;
> +	int ret;
> +
> +	rst = devm_reset_control_get_optional_exclusive(&st->spi->dev, NULL);
> +	if (IS_ERR(rst))
> +		return PTR_ERR(rst);
> +
> +	if (rst) {
> +		ret = reset_control_assert(rst);
> +		if (ret)
> +			return ret;
> +
> +		ret = reset_control_deassert(rst);

[Severity: Medium]
Does the hardware require a minimum reset pulse width? Calling 
reset_control_assert() and reset_control_deassert() sequentially without a 
delay usually generates a sub-microsecond pulse that might be too short 
for the device to properly initialize.

> +		if (ret)
> +			return ret;
> +	} else {

[ ... ]

> +static int ad5529r_read_raw(struct iio_dev *indio_dev,
> +			    struct iio_chan_spec const *chan,
> +			    int *val, int *val2, long mask)
> +{
> +	struct ad5529r_state *st = iio_priv(indio_dev);
> +	unsigned int reg_addr, reg_val_h;
> +	int ret, range_idx, span_mv;
> +
> +	switch (mask) {
> +	case IIO_CHAN_INFO_RAW:
> +		/*
> +		 * Read from DAC_INPUT_A register rather than DAC_DATA_READBACK.
> +		 * The DAC operates in transparent mode and directly reflects
> +		 * whatever value is written to the INPUT_A register.
> +		 */
> +		reg_addr = AD5529R_REG_DAC_INPUT_A(chan->channel);
> +		ret = regmap_read(st->regmap_16bit, reg_addr, &reg_val_h);
> +		if (ret)
> +			return ret;
> +
> +		*val = reg_val_h;

[Severity: Medium]
Does the 12-bit variant of this chip expect left-aligned data in the 16-bit 
register? If so, reading the unshifted register value could return incorrect 
scale data for the 12-bit device.

> +
> +		return IIO_VAL_INT;

[ ... ]

> +static int ad5529r_write_raw(struct iio_dev *indio_dev,
> +			     struct iio_chan_spec const *chan,
> +			     int val, int val2, long mask)
> +{
> +	struct ad5529r_state *st = iio_priv(indio_dev);
> +	unsigned int reg_addr;
> +
> +	switch (mask) {
> +	case IIO_CHAN_INFO_RAW:
> +		if (val < 0 || val > GENMASK(st->model_data->resolution - 1, 0))
> +			return -EINVAL;
> +
> +		reg_addr = AD5529R_REG_DAC_INPUT_A(chan->channel);
> +
> +		return regmap_write(st->regmap_16bit, reg_addr, val);

[Severity: Medium]
Similar to the read path, if the 12-bit payload needs to be left-aligned, 
writing it directly here without shifting could cause the hardware to 
interpret it as a much smaller value. Should this value be shifted based on 
the device resolution?

> +	default:
> +		return -EINVAL;
> +	}
> +}

[ ... ]

> +static int ad5529r_parse_channel_ranges(struct device *dev,
> +					struct ad5529r_state *st)
> +{
> +	s32 vals[2];
> +	int ret, range_idx;
> +	u32 ch;
> +
> +	device_for_each_child_node_scoped(dev, child) {
> +		ret = fwnode_property_read_u32(child, "reg", &ch);
> +		if (ret)
> +			return dev_err_probe(dev, ret,
> +					     "Missing reg property in channel node\n");
> +
> +		if (ch >= 16)
> +			return dev_err_probe(dev, -EINVAL,
> +					     "Channel %u exceeds maximum 15\n",
> +					     ch);

[ ... ]

> +		st->output_range_idx[ch] = range_idx;
> +		ret = regmap_write(st->regmap_16bit,
> +				   AD5529R_REG_OUT_RANGE(ch), range_idx);
> +		if (ret)
> +			return dev_err_probe(dev, ret,
> +					     "Failed to configure range for ch %u\n",
> +					     ch);
> +
> +		st->channels[st->num_channels++] = AD5529R_DAC_CHANNEL(ch);

[Severity: High]
Could this overflow the channels array? While there is a check for ch >= 16 
above, there doesn't seem to be a check on the total number of child nodes. 
If a malformed device tree provides more than 16 child nodes (for instance, 
by duplicating reg properties), st->num_channels could exceed 15 and write 
out of bounds.

> +	}
> +
> +	return 0;
> +}

[ ... ]

> +static int ad5529r_probe(struct spi_device *spi)
> +{

[ ... ]

> +	ret = devm_regulator_get_enable_optional(dev, "vref");
> +	if (ret == -ENODEV)
> +		external_vref = false;
> +	else if (!ret)
> +		external_vref = true;

[Severity: Medium]
Can this result in incorrect regulator configuration if CONFIG_REGULATOR is 
disabled? The dummy implementation of devm_regulator_get_enable_optional() 
returns 0 in that case, which would cause this to set external_vref = true 
and disable the internal reference even if no external reference exists on 
the board.

> +	else
> +		return dev_err_probe(dev, ret,
> +				     "Failed to get and enable vref regulator\n");

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260715-ad5529r-driver-v6-0-cfdf8b9f5ee3@analog.com?part=5