[PATCH v4 00/12] New features for the AD5686 IIO driver

[PATCH v4 00/12] New features for the AD5686 IIO driver

[Rodrigo Alencar via B4 Relay]

This is the second series of three on updating the AD5686 driver.

Initially, a big patch series was sent:
https://lore.kernel.org/r/20260422-ad5313r-iio-support-v1-0-ed7dca001d1b@analog.com

Then, the first patch series added fixes and cleanups:
https://lore.kernel.org/linux-iio/20260524-ad5686-fixes-v7-0-b6bf395d08bd@analog.com/

This one is introducing new features:
- Consume optional reset and correct power supplies;
- LDAC GPIO handling (active-low, held low when unused);
- SPI bus sync() implementation for batching multiple transfers;
- Triggered buffer support, leveraging LDAC and sync() to flush
  all channel writes atomically;
- Gain control support through the scale property.

Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
Changes in v4:
- Replace anyof+const for enum in dt-bindings. 
- Address some sashiko's comments.
- Use guard(mutex)() in trigger handler and other misc changes.
- Link to v3: https://lore.kernel.org/r/20260616-ad5686-new-features-v3-0-f829fb7e9262@analog.com

Changes in v3:
- Add range-double property.
- Acquire reset control after power-up delay.
- Include cleanup.h and use guard(mutex)() in read_raw().
- Link to v2: https://lore.kernel.org/r/20260609-ad5686-new-features-v2-0-70b423f5c76d@analog.com

Changes in v2:
- Get reset control deasserted.
- Update entire spi_transfer struct rather than individual fields.
- Replace udelay() for fsleep() in probe().
- Minor changes addressing further feedback.
- Link to v1: https://lore.kernel.org/r/20260602-ad5686-new-features-v1-0-691e01883d27@analog.com

---
Rodrigo Alencar (12):
      dt-bindings: iio: dac: ad5696: add reset/ldac/gain support
      dt-bindings: iio: dac: ad5696: rework on power supplies
      dt-bindings: iio: dac: ad5686: add reset/ldac/gain support
      dt-bindings: iio: dac: ad5686: rework on power supplies
      iio: dac: ad5686: add support for missing power supplies
      iio: dac: ad5686: consume optional reset signal
      iio: dac: ad5686: add ldac gpio
      iio: dac: ad5686: introduce sync operation
      iio: dac: ad5686: implement new sync() op for the spi bus
      iio: dac: ad5686: read_raw/write_raw: use guard(mutex)()
      iio: dac: ad5686: add triggered buffer support
      iio: dac: ad5686: add gain control support

 .../devicetree/bindings/iio/dac/adi,ad5686.yaml    |  72 +++++-
 .../devicetree/bindings/iio/dac/adi,ad5696.yaml    |  73 +++++-
 drivers/iio/dac/Kconfig                            |   2 +
 drivers/iio/dac/ad5686-spi.c                       | 125 +++++++---
 drivers/iio/dac/ad5686.c                           | 251 +++++++++++++++++++--
 drivers/iio/dac/ad5686.h                           |  34 ++-
 drivers/iio/dac/ad5696-i2c.c                       |   2 +-
 7 files changed, 498 insertions(+), 61 deletions(-)
---
base-commit: a50909aa46dec46de3c73235fc15a7d6f763d996
change-id: 20260602-ad5686-new-features-e116c04bddb9

Best regards,
-- 
Rodrigo Alencar <rodrigo.alencar@analog.com>

[PATCH v4 01/12] dt-bindings: iio: dac: ad5696: add reset/ldac/gain support

[Rodrigo Alencar via B4 Relay]

From: Rodrigo Alencar <rodrigo.alencar@analog.com>

Add GPIO property for RESET, LDAC and GAIN pin. RESET is active-low, LDAC
is used to load DAC channels with values from input registers and GAIN
can double the voltage in output channels. The gain-gpios property is
not available to all supported parts. The adi,range-double property
indicates that GAIN pin is hardwired to high in case gain-gpios is not
set, otherwise it sets the initial value for the gain setting.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
 .../devicetree/bindings/iio/dac/adi,ad5696.yaml    | 39 ++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml
index b5a88b03dc2f..cc343cdf6085 100644
--- a/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml
+++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml
@@ -37,14 +37,52 @@ properties:
     description: |
       The regulator supply for DAC reference voltage.
 
+  reset-gpios:
+    description: Active-low RESET pin to reset the device.
+    maxItems: 1
+
+  ldac-gpios:
+    description:
+      Active-low LDAC pin used to asynchronously update the DAC channels.
+    maxItems: 1
+
+  gain-gpios:
+    description:
+      GAIN pin that sets a multiplier for the DAC output voltage. When high,
+      the DAC output voltage is multiplied by 2, otherwise it is unchanged.
+    maxItems: 1
+
+  adi,range-double:
+    description:
+      Sets the initial voltage output range from 0 to 2xVREF. On devices that
+      have a GAIN pin and no gain-gpios property is set, this indicates the pin
+      is hardwired high.
+    type: boolean
+
 required:
   - compatible
   - reg
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - adi,ad5311r
+              - adi,ad5691r
+              - adi,ad5692r
+              - adi,ad5693
+              - adi,ad5693r
+    then:
+      properties:
+        gain-gpios: false
+
 additionalProperties: false
 
 examples:
   - |
+    #include <dt-bindings/gpio/gpio.h>
     i2c {
       #address-cells = <1>;
       #size-cells = <0>;
@@ -53,6 +91,7 @@ examples:
         compatible = "adi,ad5696";
         reg = <0>;
         vcc-supply = <&dac_vref>;
+        ldac-gpios = <&gpio0 1 GPIO_ACTIVE_LOW>;
       };
     };
 ...

-- 
2.43.0

[PATCH v4 02/12] dt-bindings: iio: dac: ad5696: rework on power supplies

[Rodrigo Alencar via B4 Relay]

From: Rodrigo Alencar <rodrigo.alencar@analog.com>

Add supplies for VDD, VLOGIC and VREF input voltage pins. The vcc-supply
property is deprecated, once it does not really exist as none of the
devices describe any power input with that name. VCC is also misleading as
it sounds like the input power supply, but it is being used as an external
voltage reference, which should be called VREF. Certain devices require
vref-supply to be available once an internal reference voltage is absent.
For correct operation vdd and vlogic supplies are required.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
 .../devicetree/bindings/iio/dac/adi,ad5696.yaml    | 34 ++++++++++++++++++++--
 1 file changed, 31 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml
index cc343cdf6085..e10f8596f9d3 100644
--- a/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml
+++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml
@@ -33,9 +33,22 @@ properties:
   reg:
     maxItems: 1
 
+  vdd-supply:
+    description: Input power supply.
+
+  vlogic-supply:
+    description:
+      Digital power supply. On some tiny package variants for single-channel
+      devices, this supply is internally connected to vdd; in that case, specify
+      this property with the same regulator as vdd.
+
+  vref-supply:
+    description:
+      Reference voltage supply. If not supplied the internal reference is used.
+
   vcc-supply:
-    description: |
-      The regulator supply for DAC reference voltage.
+    deprecated: true
+    description: Use vref-supply instead.
 
   reset-gpios:
     description: Active-low RESET pin to reset the device.
@@ -62,8 +75,21 @@ properties:
 required:
   - compatible
   - reg
+  - vdd-supply
+  - vlogic-supply
 
 allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - adi,ad5693
+              - adi,ad5694
+              - adi,ad5696
+    then:
+      required:
+        - vref-supply
   - if:
       properties:
         compatible:
@@ -90,7 +116,9 @@ examples:
       ad5696: dac@0 {
         compatible = "adi,ad5696";
         reg = <0>;
-        vcc-supply = <&dac_vref>;
+        vdd-supply = <&dac_vdd>;
+        vlogic-supply = <&dac_vlogic>;
+        vref-supply = <&dac_vref>;
         ldac-gpios = <&gpio0 1 GPIO_ACTIVE_LOW>;
       };
     };

-- 
2.43.0

[PATCH v4 03/12] dt-bindings: iio: dac: ad5686: add reset/ldac/gain support

[Rodrigo Alencar via B4 Relay]

From: Rodrigo Alencar <rodrigo.alencar@analog.com>

Add GPIO property for RESET, LDAC and GAIN pin. RESET is active-low, LDAC
is used to load DAC channels with values from input registers and GAIN
can double the voltage in output channels. The gain-gpios property is
not available to all supported parts. The adi,range-double property
indicates that GAIN pin is hardwired to high in case gain-gpios is not
set, otherwise it sets the initial value for the gain setting.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
 .../devicetree/bindings/iio/dac/adi,ad5686.yaml    | 38 ++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5686.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5686.yaml
index 713f535bb33a..d781baca6a6c 100644
--- a/Documentation/devicetree/bindings/iio/dac/adi,ad5686.yaml
+++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5686.yaml
@@ -35,17 +35,53 @@ properties:
   vcc-supply:
     description: If not supplied the internal reference is used.
 
+  reset-gpios:
+    description: Active-low RESET pin to reset the device.
+    maxItems: 1
+
+  ldac-gpios:
+    description:
+      Active-low LDAC pin used to asynchronously update the DAC channels.
+    maxItems: 1
+
+  gain-gpios:
+    description:
+      GAIN pin that sets a multiplier for the DAC output voltage. When high,
+      the DAC output voltage is multiplied by 2, otherwise it is unchanged.
+    maxItems: 1
+
+  adi,range-double:
+    description:
+      Sets the initial voltage output range from 0 to 2xVREF. On devices that
+      have a GAIN pin and no gain-gpios property is set, this indicates the pin
+      is hardwired high.
+    type: boolean
+
 required:
   - compatible
   - reg
 
 allOf:
   - $ref: /schemas/spi/spi-peripheral-props.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - adi,ad5310r
+              - adi,ad5681r
+              - adi,ad5682r
+              - adi,ad5683
+              - adi,ad5683r
+    then:
+      properties:
+        gain-gpios: false
 
 unevaluatedProperties: false
 
 examples:
   - |
+    #include <dt-bindings/gpio/gpio.h>
     spi {
         #address-cells = <1>;
         #size-cells = <0>;
@@ -53,6 +89,8 @@ examples:
             reg = <0>;
             compatible = "adi,ad5310r";
             vcc-supply = <&dac_vref0>;
+            reset-gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
+            ldac-gpios = <&gpio0 1 GPIO_ACTIVE_LOW>;
         };
     };
 ...

-- 
2.43.0

[PATCH v4 04/12] dt-bindings: iio: dac: ad5686: rework on power supplies

[Rodrigo Alencar via B4 Relay]

From: Rodrigo Alencar <rodrigo.alencar@analog.com>

Add supplies for VDD, VLOGIC and VREF input voltage pins. The vcc-supply
property is deprecated, once it does not really exist as none of the
devices describe any power input with that name. VCC is also misleading as
it sounds like the input power supply, but it is being used as an external
voltage reference, which should be called VREF. Certain devices require
vref-supply to be available once an internal reference voltage is absent.
For correct operation vdd and vlogic supplies are required.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
 .../devicetree/bindings/iio/dac/adi,ad5686.yaml    | 34 ++++++++++++++++++++--
 1 file changed, 32 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5686.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5686.yaml
index d781baca6a6c..02e8c78e36d3 100644
--- a/Documentation/devicetree/bindings/iio/dac/adi,ad5686.yaml
+++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5686.yaml
@@ -32,8 +32,22 @@ properties:
   reg:
     maxItems: 1
 
+  vdd-supply:
+    description: Input power supply.
+
+  vlogic-supply:
+    description:
+      Digital power supply. On some tiny package variants for single-channel
+      devices, this supply is internally connected to vdd; in that case, specify
+      this property with the same regulator as vdd.
+
+  vref-supply:
+    description:
+      Reference voltage supply. If not supplied the internal reference is used.
+
   vcc-supply:
-    description: If not supplied the internal reference is used.
+    deprecated: true
+    description: Use vref-supply instead.
 
   reset-gpios:
     description: Active-low RESET pin to reset the device.
@@ -60,9 +74,23 @@ properties:
 required:
   - compatible
   - reg
+  - vdd-supply
+  - vlogic-supply
 
 allOf:
   - $ref: /schemas/spi/spi-peripheral-props.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - adi,ad5676
+              - adi,ad5683
+              - adi,ad5684
+              - adi,ad5686
+    then:
+      required:
+        - vref-supply
   - if:
       properties:
         compatible:
@@ -88,7 +116,9 @@ examples:
         dac@0 {
             reg = <0>;
             compatible = "adi,ad5310r";
-            vcc-supply = <&dac_vref0>;
+            vdd-supply = <&dac_vdd>;
+            vlogic-supply = <&dac_vlogic>;
+            vref-supply = <&dac_vref>;
             reset-gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
             ldac-gpios = <&gpio0 1 GPIO_ACTIVE_LOW>;
         };

-- 
2.43.0

[PATCH v4 05/12] iio: dac: ad5686: add support for missing power supplies

[Rodrigo Alencar via B4 Relay]

From: Rodrigo Alencar <rodrigo.alencar@analog.com>

Get and enable regulators for vdd, vlogic and vref input power pins. Vdd
is the input power supply, while vlogic powers the digital side. vref is
replacing vcc, which is being deprecated, but still supported. The value
of vref_mv is checked so that a device without internal voltage reference
cannot proceed without an explicit supply. For correct operation, vdd and
vlogic are required, then devm_regulator_get_enable() is used so the
driver can still work without them by using the stub/dummy regulators.
Error report uses dev_err_probe(), which helps debugging an init issue.
A small delay is added after the regulators are enabled to consider for
the power-up time (4.5 us).

Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
 drivers/iio/dac/ad5686.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
index 5840fda4b011..e2ebabca6887 100644
--- a/drivers/iio/dac/ad5686.c
+++ b/drivers/iio/dac/ad5686.c
@@ -8,6 +8,8 @@
 #include <linux/array_size.h>
 #include <linux/bitfield.h>
 #include <linux/bitops.h>
+#include <linux/delay.h>
+#include <linux/dev_printk.h>
 #include <linux/errno.h>
 #include <linux/export.h>
 #include <linux/kstrtox.h>
@@ -484,12 +486,28 @@ int ad5686_probe(struct device *dev,
 	st->ops = ops;
 	st->chip_info = chip_info;
 
-	ret = devm_regulator_get_enable_read_voltage(dev, "vcc");
+	ret = devm_regulator_get_enable(dev, "vdd");
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to enable vdd supply\n");
+
+	ret = devm_regulator_get_enable(dev, "vlogic");
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to enable vlogic supply\n");
+
+	ret = devm_regulator_get_enable_read_voltage(dev, "vref");
+	if (ret == -ENODEV) /* vcc-supply is deprecated, but supported still */
+		ret = devm_regulator_get_enable_read_voltage(dev, "vcc");
 	if (ret < 0 && ret != -ENODEV)
-		return ret;
+		return dev_err_probe(dev, ret, "failed to read vref voltage\n");
 
 	st->use_internal_vref = ret == -ENODEV;
 	st->vref_mv = st->use_internal_vref ? st->chip_info->int_vref_mv : ret / 1000;
+	if (!st->vref_mv)
+		return dev_err_probe(dev, -EINVAL,
+				     "invalid or not provided vref voltage\n");
+
+	/* 4.5us power-up time: Datasheet Table 4: Timing Characteristics */
+	fsleep(5);
 
 	/* Initialize masks to all ones */
 	st->pwr_down_mask = ~0;

-- 
2.43.0

[PATCH v4 06/12] iio: dac: ad5686: consume optional reset signal

[Rodrigo Alencar via B4 Relay]

From: Rodrigo Alencar <rodrigo.alencar@analog.com>

Add RESET pin GPIO support through an optional reset control, which is
local to the probe function. A reset pulse is manually generated after
the device is powered up.

Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
 drivers/iio/dac/ad5686.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
index e2ebabca6887..8ad8931a3d7f 100644
--- a/drivers/iio/dac/ad5686.c
+++ b/drivers/iio/dac/ad5686.c
@@ -15,6 +15,7 @@
 #include <linux/kstrtox.h>
 #include <linux/module.h>
 #include <linux/regulator/consumer.h>
+#include <linux/reset.h>
 #include <linux/sysfs.h>
 #include <linux/wordpart.h>
 
@@ -472,6 +473,7 @@ int ad5686_probe(struct device *dev,
 		 const struct ad5686_chip_info *chip_info,
 		 const char *name, const struct ad5686_bus_ops *ops)
 {
+	struct reset_control *rstc;
 	struct ad5686_state *st;
 	struct iio_dev *indio_dev;
 	int ret, i;
@@ -486,6 +488,11 @@ int ad5686_probe(struct device *dev,
 	st->ops = ops;
 	st->chip_info = chip_info;
 
+	rstc = devm_reset_control_get_optional_exclusive(dev, NULL);
+	if (IS_ERR(rstc))
+		return dev_err_probe(dev, PTR_ERR(rstc),
+				     "Failed to get reset control\n");
+
 	ret = devm_regulator_get_enable(dev, "vdd");
 	if (ret)
 		return dev_err_probe(dev, ret, "failed to enable vdd supply\n");
@@ -509,6 +516,11 @@ int ad5686_probe(struct device *dev,
 	/* 4.5us power-up time: Datasheet Table 4: Timing Characteristics */
 	fsleep(5);
 
+	/* 1us >> 30ns reset pulse activation time: Datasheet Table 4 */
+	reset_control_assert(rstc);
+	fsleep(1);
+	reset_control_deassert(rstc);
+
 	/* Initialize masks to all ones */
 	st->pwr_down_mask = ~0;
 	st->pwr_down_mode = ~0;

-- 
2.43.0

[PATCH v4 07/12] iio: dac: ad5686: add ldac gpio

[Rodrigo Alencar via B4 Relay]

From: Rodrigo Alencar <rodrigo.alencar@analog.com>

If wired LDAC, should be asserted when unused (pin is active-low), which
allows for synchronous DAC updates. This will be used to update all the
channels at the same time when adding buffer support.

Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
 drivers/iio/dac/ad5686.c | 6 ++++++
 drivers/iio/dac/ad5686.h | 4 ++++
 2 files changed, 10 insertions(+)

diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
index 8ad8931a3d7f..713fe71ad1e7 100644
--- a/drivers/iio/dac/ad5686.c
+++ b/drivers/iio/dac/ad5686.c
@@ -12,6 +12,7 @@
 #include <linux/dev_printk.h>
 #include <linux/errno.h>
 #include <linux/export.h>
+#include <linux/gpio/consumer.h>
 #include <linux/kstrtox.h>
 #include <linux/module.h>
 #include <linux/regulator/consumer.h>
@@ -521,6 +522,11 @@ int ad5686_probe(struct device *dev,
 	fsleep(1);
 	reset_control_deassert(rstc);
 
+	st->ldac_gpio = devm_gpiod_get_optional(dev, "ldac", GPIOD_OUT_HIGH);
+	if (IS_ERR(st->ldac_gpio))
+		return dev_err_probe(dev, PTR_ERR(st->ldac_gpio),
+				     "Failed to get LDAC GPIO\n");
+
 	/* Initialize masks to all ones */
 	st->pwr_down_mask = ~0;
 	st->pwr_down_mode = ~0;
diff --git a/drivers/iio/dac/ad5686.h b/drivers/iio/dac/ad5686.h
index a06fe7d89305..c424720f8f72 100644
--- a/drivers/iio/dac/ad5686.h
+++ b/drivers/iio/dac/ad5686.h
@@ -60,6 +60,8 @@ enum ad5686_regmap_type {
 	AD5686_REGMAP,
 };
 
+struct gpio_desc;
+
 struct ad5686_state;
 
 /**
@@ -119,6 +121,7 @@ extern const struct ad5686_chip_info ad5679r_chip_info;
  * @dev:		device instance
  * @chip_info:		chip model specific constants, available modes etc
  * @ops:		bus specific operations
+ * @ldac_gpio:		LDAC pin GPIO descriptor
  * @vref_mv:		actual reference voltage used
  * @pwr_down_mask:	power down mask
  * @pwr_down_mode:	current power down mode
@@ -131,6 +134,7 @@ struct ad5686_state {
 	struct device			*dev;
 	const struct ad5686_chip_info	*chip_info;
 	const struct ad5686_bus_ops	*ops;
+	struct gpio_desc		*ldac_gpio;
 	unsigned short			vref_mv;
 	unsigned int			pwr_down_mask;
 	unsigned int			pwr_down_mode;

-- 
2.43.0

[PATCH v4 08/12] iio: dac: ad5686: introduce sync operation

[Rodrigo Alencar via B4 Relay]

From: Rodrigo Alencar <rodrigo.alencar@analog.com>

Add sync() to operation to ad5686_bus_ops, which can be used to flush
multiple pending data transfers at once. This is going to be used when
implementing triggered buffer support.

Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
 drivers/iio/dac/ad5686.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/dac/ad5686.h b/drivers/iio/dac/ad5686.h
index c424720f8f72..9a192b0a2d7a 100644
--- a/drivers/iio/dac/ad5686.h
+++ b/drivers/iio/dac/ad5686.h
@@ -68,10 +68,12 @@ struct ad5686_state;
  * struct ad5686_bus_ops - bus specific read/write operations
  * @read: read a register value at the given address
  * @write: write a command, address and value to the device
+ * @sync: ensure the completion of the write operation (optional)
  */
 struct ad5686_bus_ops {
 	int (*read)(struct ad5686_state *st, u8 addr);
 	int (*write)(struct ad5686_state *st, u8 cmd, u8 addr, u16 val);
+	int (*sync)(struct ad5686_state *st);
 };
 
 /**
@@ -160,7 +162,13 @@ int ad5686_probe(struct device *dev,
 
 static inline int ad5686_write(struct ad5686_state *st, u8 cmd, u8 addr, u16 val)
 {
-	return st->ops->write(st, cmd, addr, val);
+	int ret;
+
+	ret = st->ops->write(st, cmd, addr, val);
+	if (ret)
+		return ret;
+
+	return st->ops->sync ? st->ops->sync(st) : 0;
 }
 
 static inline int ad5686_read(struct ad5686_state *st, u8 addr)

-- 
2.43.0

[PATCH v4 09/12] iio: dac: ad5686: implement new sync() op for the spi bus

[Rodrigo Alencar via B4 Relay]

From: Rodrigo Alencar <rodrigo.alencar@analog.com>

Use of local SPI bus data to manage a collection of SPI transfers and
flush them to the SPI platform driver with the sync() operation. This
allows for faster handling of multiple channel DAC writes, avoiding kernel
overhead per spi_sync() call, which will be helpful when enabling
triggered buffer support.

Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
 drivers/iio/dac/ad5686-spi.c | 125 ++++++++++++++++++++++++++++++++-----------
 drivers/iio/dac/ad5686.c     |   4 +-
 drivers/iio/dac/ad5686.h     |   8 ++-
 drivers/iio/dac/ad5696-i2c.c |   2 +-
 4 files changed, 104 insertions(+), 35 deletions(-)

diff --git a/drivers/iio/dac/ad5686-spi.c b/drivers/iio/dac/ad5686-spi.c
index 6b6ef1d7071f..4a9a365b63bc 100644
--- a/drivers/iio/dac/ad5686-spi.c
+++ b/drivers/iio/dac/ad5686-spi.c
@@ -12,59 +12,91 @@
 #include <linux/errno.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
+#include <linux/overflow.h>
 #include <linux/spi/spi.h>
 
 #include <asm/byteorder.h>
 
 #include "ad5686.h"
 
+/**
+ * struct ad5686_spi_data - SPI bus specific data
+ * @msg: SPI message used for transfers
+ * @size: number of transfers currently in the message
+ * @capacity: maximum number of transfers that can be added to the message
+ * @xfers: array of SPI transfers, allocated with the provided capacity
+ */
+struct ad5686_spi_data {
+	struct spi_message msg;
+	unsigned int size;
+	unsigned int capacity;
+	struct spi_transfer xfers[] __counted_by(capacity);
+};
+
 static int ad5686_spi_write(struct ad5686_state *st,
 			    u8 cmd, u8 addr, u16 val)
 {
-	struct spi_device *spi = to_spi_device(st->dev);
-	u8 tx_len, *buf;
+	struct ad5686_spi_data *bus_data = st->bus_data;
+	struct spi_transfer *xfer;
 
+	if (bus_data->size >= bus_data->capacity)
+		return -E2BIG;
+
+	if (bus_data->size)
+		bus_data->xfers[bus_data->size - 1].cs_change = 1;
+	else
+		spi_message_init(&bus_data->msg);
+
+	xfer = &bus_data->xfers[bus_data->size];
 	switch (st->chip_info->regmap_type) {
 	case AD5310_REGMAP:
-		st->data[0].d16 = cpu_to_be16(AD5310_CMD(cmd) |
-					      val);
-		buf = &st->data[0].d8[0];
-		tx_len = 2;
+		st->data[bus_data->size].d16 =
+			cpu_to_be16(AD5310_CMD(cmd) | val);
+		*xfer = (struct spi_transfer) {
+			.tx_buf = &st->data[bus_data->size].d16,
+			.len = sizeof(st->data[bus_data->size].d16),
+		};
 		break;
 	case AD5683_REGMAP:
-		st->data[0].d32 = cpu_to_be32(AD5686_CMD(cmd) |
-					      AD5683_DATA(val));
-		buf = &st->data[0].d8[1];
-		tx_len = 3;
+		st->data[bus_data->size].d32 =
+			cpu_to_be32(AD5686_CMD(cmd) | AD5683_DATA(val));
+		*xfer = (struct spi_transfer) {
+			.tx_buf = &st->data[bus_data->size].d8[1],
+			.len = sizeof(st->data[bus_data->size].d8) - 1,
+		};
 		break;
 	case AD5686_REGMAP:
-		st->data[0].d32 = cpu_to_be32(AD5686_CMD(cmd) |
-					      AD5686_ADDR(addr) |
-					      val);
-		buf = &st->data[0].d8[1];
-		tx_len = 3;
+		st->data[bus_data->size].d32 =
+			cpu_to_be32(AD5686_CMD(cmd) | AD5686_ADDR(addr) | val);
+		*xfer = (struct spi_transfer) {
+			.tx_buf = &st->data[bus_data->size].d8[1],
+			.len = sizeof(st->data[bus_data->size].d8) - 1,
+		};
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	return spi_write(spi, buf, tx_len);
+	spi_message_add_tail(xfer, &bus_data->msg);
+	bus_data->size++;
+
+	return 0;
+}
+
+static int ad5686_spi_sync(struct ad5686_state *st)
+{
+	struct spi_device *spi = to_spi_device(st->dev);
+	struct ad5686_spi_data *bus_data = st->bus_data;
+
+	bus_data->size = 0; /* always reset, even on sync failure */
+	return spi_sync(spi, &bus_data->msg);
 }
 
 static int ad5686_spi_read(struct ad5686_state *st, u8 addr)
 {
-	struct spi_transfer t[] = {
-		{
-			.tx_buf = &st->data[0].d8[1],
-			.len = 3,
-			.cs_change = 1,
-		}, {
-			.tx_buf = &st->data[1].d8[1],
-			.rx_buf = &st->data[2].d8[1],
-			.len = 3,
-		},
-	};
 	struct spi_device *spi = to_spi_device(st->dev);
+	struct ad5686_spi_data *bus_data = st->bus_data;
+	struct spi_transfer *xfer = &bus_data->xfers[0];
 	u8 cmd = 0;
 	int ret;
 
@@ -85,8 +117,21 @@ static int ad5686_spi_read(struct ad5686_state *st, u8 addr)
 				      AD5686_ADDR(addr));
 	st->data[1].d32 = cpu_to_be32(AD5686_CMD(AD5686_CMD_NOOP));
 
-	ret = spi_sync_transfer(spi, t, ARRAY_SIZE(t));
-	if (ret < 0)
+	xfer[0] = (struct spi_transfer) {
+		.tx_buf = &st->data[0].d8[1],
+		.len = sizeof(st->data[0].d8) - 1,
+		.cs_change = 1,
+	};
+	xfer[1] = (struct spi_transfer) {
+		.tx_buf = &st->data[1].d8[1],
+		.rx_buf = &st->data[2].d8[1],
+		.len = sizeof(st->data[1].d8) - 1,
+	};
+
+	spi_message_init_with_transfers(&bus_data->msg, xfer, 2);
+
+	ret = spi_sync(spi, &bus_data->msg);
+	if (ret)
 		return ret;
 
 	return be32_to_cpu(st->data[2].d32);
@@ -95,12 +140,30 @@ static int ad5686_spi_read(struct ad5686_state *st, u8 addr)
 static const struct ad5686_bus_ops ad5686_spi_ops = {
 	.write = ad5686_spi_write,
 	.read = ad5686_spi_read,
+	.sync = ad5686_spi_sync,
 };
 
 static int ad5686_spi_probe(struct spi_device *spi)
 {
-	return ad5686_probe(&spi->dev, spi_get_device_match_data(spi),
-			    spi->modalias, &ad5686_spi_ops);
+	const struct ad5686_chip_info *info;
+	struct ad5686_spi_data *bus_data;
+	struct device *dev = &spi->dev;
+	unsigned int capacity;
+
+	info = spi_get_device_match_data(spi);
+	if (!info)
+		return -ENODEV;
+
+	/* read operation requires at least 2 transfers */
+	capacity = max(info->num_channels, 2);
+	bus_data = devm_kzalloc(dev, struct_size(bus_data, xfers, capacity),
+				GFP_KERNEL);
+	if (!bus_data)
+		return -ENOMEM;
+
+	bus_data->capacity = capacity;
+
+	return ad5686_probe(dev, info, spi->modalias, &ad5686_spi_ops, bus_data);
 }
 
 static const struct spi_device_id ad5686_spi_id[] = {
diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
index 713fe71ad1e7..75dd7921c67b 100644
--- a/drivers/iio/dac/ad5686.c
+++ b/drivers/iio/dac/ad5686.c
@@ -472,7 +472,8 @@ EXPORT_SYMBOL_NS_GPL(ad5679r_chip_info, "IIO_AD5686");
 
 int ad5686_probe(struct device *dev,
 		 const struct ad5686_chip_info *chip_info,
-		 const char *name, const struct ad5686_bus_ops *ops)
+		 const char *name, const struct ad5686_bus_ops *ops,
+		 void *bus_data)
 {
 	struct reset_control *rstc;
 	struct ad5686_state *st;
@@ -487,6 +488,7 @@ int ad5686_probe(struct device *dev,
 
 	st->dev = dev;
 	st->ops = ops;
+	st->bus_data = bus_data;
 	st->chip_info = chip_info;
 
 	rstc = devm_reset_control_get_optional_exclusive(dev, NULL);
diff --git a/drivers/iio/dac/ad5686.h b/drivers/iio/dac/ad5686.h
index 9a192b0a2d7a..cb884334e94a 100644
--- a/drivers/iio/dac/ad5686.h
+++ b/drivers/iio/dac/ad5686.h
@@ -23,6 +23,7 @@
 
 #define AD5686_ADDR_DAC(chan)			(0x1 << (chan))
 #define AD5686_ADDR_ALL_DAC			0xF
+#define AD5686_MAX_CHANNELS			16
 
 #define AD5686_CMD_NOOP				0x0
 #define AD5686_CMD_WRITE_INPUT_N		0x1
@@ -130,6 +131,7 @@ extern const struct ad5686_chip_info ad5679r_chip_info;
  * @use_internal_vref:	set to true if the internal reference voltage is used
  * @lock:		lock to protect access to state fields, which includes
  *			the data buffer during regmap ops
+ * @bus_data:		bus specific data
  * @data:		transfer buffers
  */
 struct ad5686_state {
@@ -142,6 +144,7 @@ struct ad5686_state {
 	unsigned int			pwr_down_mode;
 	bool				use_internal_vref;
 	struct mutex			lock;
+	void				*bus_data;
 
 	/*
 	 * DMA (thus cache coherency maintenance) may require the
@@ -152,13 +155,14 @@ struct ad5686_state {
 		__be32 d32;
 		__be16 d16;
 		u8 d8[4];
-	} data[3] __aligned(IIO_DMA_MINALIGN);
+	} data[AD5686_MAX_CHANNELS] __aligned(IIO_DMA_MINALIGN);
 };
 
 
 int ad5686_probe(struct device *dev,
 		 const struct ad5686_chip_info *chip_info,
-		 const char *name, const struct ad5686_bus_ops *ops);
+		 const char *name, const struct ad5686_bus_ops *ops,
+		 void *bus_data);
 
 static inline int ad5686_write(struct ad5686_state *st, u8 cmd, u8 addr, u16 val)
 {
diff --git a/drivers/iio/dac/ad5696-i2c.c b/drivers/iio/dac/ad5696-i2c.c
index 279309329b64..28c97ded43ce 100644
--- a/drivers/iio/dac/ad5696-i2c.c
+++ b/drivers/iio/dac/ad5696-i2c.c
@@ -70,7 +70,7 @@ static const struct ad5686_bus_ops ad5686_i2c_ops = {
 static int ad5686_i2c_probe(struct i2c_client *i2c)
 {
 	return ad5686_probe(&i2c->dev, i2c_get_match_data(i2c),
-			    i2c->name, &ad5686_i2c_ops);
+			    i2c->name, &ad5686_i2c_ops, NULL);
 }
 
 static const struct i2c_device_id ad5686_i2c_id[] = {

-- 
2.43.0

[PATCH v4 10/12] iio: dac: ad5686: read_raw/write_raw: use guard(mutex)()

[Rodrigo Alencar via B4 Relay]

From: Rodrigo Alencar <rodrigo.alencar@analog.com>

Use guarded mutex lock to facilitate code review when adding new
attributes. This will allow for early returns, avoiding error-prone
locking and unlocking in error paths. This also adds missing include
linux/cleanup.h. Gain-control support will allow the scale attribute
to be configurable.

Reviewed-by: Maxwell Doose <m32285159@gmail.com>
Reviewed-by: Joshua Crofts <joshua.crofts1@gmail.com>
Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
 drivers/iio/dac/ad5686.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
index 75dd7921c67b..db175e77b0b7 100644
--- a/drivers/iio/dac/ad5686.c
+++ b/drivers/iio/dac/ad5686.c
@@ -8,6 +8,7 @@
 #include <linux/array_size.h>
 #include <linux/bitfield.h>
 #include <linux/bitops.h>
+#include <linux/cleanup.h>
 #include <linux/delay.h>
 #include <linux/dev_printk.h>
 #include <linux/errno.h>
@@ -177,11 +178,11 @@ static int ad5686_read_raw(struct iio_dev *indio_dev,
 	struct ad5686_state *st = iio_priv(indio_dev);
 	int ret;
 
+	guard(mutex)(&st->lock);
+
 	switch (m) {
 	case IIO_CHAN_INFO_RAW:
-		mutex_lock(&st->lock);
 		ret = ad5686_read(st, chan->address);
-		mutex_unlock(&st->lock);
 		if (ret < 0)
 			return ret;
 		*val = (ret >> chan->scan_type.shift) &
@@ -202,23 +203,19 @@ static int ad5686_write_raw(struct iio_dev *indio_dev,
 			    long mask)
 {
 	struct ad5686_state *st = iio_priv(indio_dev);
-	int ret;
+
+	guard(mutex)(&st->lock);
 
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
 		if (val >= (1 << chan->scan_type.realbits) || val < 0)
 			return -EINVAL;
 
-		mutex_lock(&st->lock);
-		ret = ad5686_write(st, AD5686_CMD_WRITE_INPUT_N_UPDATE_N,
-				   chan->address, val << chan->scan_type.shift);
-		mutex_unlock(&st->lock);
-		break;
+		return ad5686_write(st, AD5686_CMD_WRITE_INPUT_N_UPDATE_N,
+				    chan->address, val << chan->scan_type.shift);
 	default:
-		ret = -EINVAL;
+		return -EINVAL;
 	}
-
-	return ret;
 }
 
 static const struct iio_info ad5686_info = {

-- 
2.43.0

[PATCH v4 11/12] iio: dac: ad5686: add triggered buffer support

[Rodrigo Alencar via B4 Relay]

From: Rodrigo Alencar <rodrigo.alencar@analog.com>

Implement trigger handler by leveraging the LDAC gpio to update all DAC
channels at once when it is available. Also, the multiple channel writes
can be flushed at once with the sync() operation.

Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
 drivers/iio/dac/Kconfig  |  2 ++
 drivers/iio/dac/ad5686.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 68 insertions(+)

diff --git a/drivers/iio/dac/Kconfig b/drivers/iio/dac/Kconfig
index 657c68e75542..5f14fcd780e2 100644
--- a/drivers/iio/dac/Kconfig
+++ b/drivers/iio/dac/Kconfig
@@ -240,6 +240,8 @@ config LTC2688
 
 config AD5686
 	tristate
+	select IIO_BUFFER
+	select IIO_TRIGGERED_BUFFER
 
 config AD5686_SPI
 	tristate "Analog Devices AD5686 and similar multi-channel DACs (SPI)"
diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
index db175e77b0b7..4dc681eb077d 100644
--- a/drivers/iio/dac/ad5686.c
+++ b/drivers/iio/dac/ad5686.c
@@ -21,7 +21,11 @@
 #include <linux/sysfs.h>
 #include <linux/wordpart.h>
 
+#include <linux/iio/buffer.h>
 #include <linux/iio/iio.h>
+#include <linux/iio/trigger.h>
+#include <linux/iio/trigger_consumer.h>
+#include <linux/iio/triggered_buffer.h>
 
 #include "ad5686.h"
 
@@ -243,6 +247,7 @@ static const struct iio_chan_spec_ext_info ad5686_ext_info[] = {
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),	\
 		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),\
 		.address = addr,				\
+		.scan_index = chan,				\
 		.scan_type = {					\
 			.sign = 'u',				\
 			.realbits = (bits),			\
@@ -467,6 +472,60 @@ const struct ad5686_chip_info ad5679r_chip_info = {
 };
 EXPORT_SYMBOL_NS_GPL(ad5679r_chip_info, "IIO_AD5686");
 
+static irqreturn_t ad5686_trigger_handler(int irq, void *p)
+{
+	struct iio_poll_func *pf = p;
+	struct iio_dev *indio_dev = pf->indio_dev;
+	struct iio_buffer *buffer = indio_dev->buffer;
+	struct ad5686_state *st = iio_priv(indio_dev);
+	u16 val[AD5686_MAX_CHANNELS] = { };
+	unsigned int scan_count, ch, i;
+	bool async_update;
+	int ret;
+	u8 cmd;
+
+	ret = iio_pop_from_buffer(buffer, val);
+	if (ret) {
+		iio_trigger_notify_done(indio_dev->trig);
+		return IRQ_HANDLED;
+	}
+
+	guard(mutex)(&st->lock);
+
+	scan_count = bitmap_weight(indio_dev->active_scan_mask,
+				   iio_get_masklength(indio_dev));
+	async_update = st->ldac_gpio && scan_count > 1;
+	if (async_update) {
+		/* use LDAC to update all channels simultaneously */
+		cmd = AD5686_CMD_WRITE_INPUT_N;
+		gpiod_set_value_cansleep(st->ldac_gpio, 0);
+	} else {
+		cmd = AD5686_CMD_WRITE_INPUT_N_UPDATE_N;
+	}
+
+	i = 0;
+	iio_for_each_active_channel(indio_dev, ch) {
+		ret = st->ops->write(st, cmd, indio_dev->channels[ch].address, val[i++]);
+		if (ret)
+			break;
+	}
+
+	/*
+	 * If sync() is available, it is called here regardless of write
+	 * failure to allow bus implementation to reset. In that case, partial
+	 * writes are unlikely as the write operations would just queue up
+	 * the transfers.
+	 */
+	if (st->ops->sync)
+		st->ops->sync(st);
+
+	if (async_update)
+		gpiod_set_value_cansleep(st->ldac_gpio, 1);
+
+	iio_trigger_notify_done(indio_dev->trig);
+	return IRQ_HANDLED;
+}
+
 int ad5686_probe(struct device *dev,
 		 const struct ad5686_chip_info *chip_info,
 		 const char *name, const struct ad5686_bus_ops *ops,
@@ -569,6 +628,13 @@ int ad5686_probe(struct device *dev,
 		return -EINVAL;
 	}
 
+	ret = devm_iio_triggered_buffer_setup_ext(dev, indio_dev, NULL,
+						  &ad5686_trigger_handler,
+						  IIO_BUFFER_DIRECTION_OUT,
+						  NULL, NULL);
+	if (ret)
+		return ret;
+
 	return devm_iio_device_register(dev, indio_dev);
 }
 EXPORT_SYMBOL_NS_GPL(ad5686_probe, "IIO_AD5686");

-- 
2.43.0

[PATCH v4 12/12] iio: dac: ad5686: add gain control support

[Rodrigo Alencar via B4 Relay]

From: Rodrigo Alencar <rodrigo.alencar@analog.com>

Most of the supported devices rely on a GAIN pin to control a 2x
multiplier applied to the output voltage. Other devices, e.g. the
single-channel ones, provides a gain control through a bit field in
the control register. Some designs might have the GAIN pin hardwired
to VDD/VLOGIC or GND, which would have no "gain-gpios" device property,
being able to set "adi,range-double" if it is hardwired to VDD. The
vref_mv field is moved down in the struct ad5686_state, so that the
overall size increase is reduced.

Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
 drivers/iio/dac/ad5686.c | 122 +++++++++++++++++++++++++++++++++++++++++++++--
 drivers/iio/dac/ad5686.h |  12 ++++-
 2 files changed, 127 insertions(+), 7 deletions(-)

diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
index 4dc681eb077d..bad214b89257 100644
--- a/drivers/iio/dac/ad5686.c
+++ b/drivers/iio/dac/ad5686.c
@@ -15,10 +15,13 @@
 #include <linux/export.h>
 #include <linux/gpio/consumer.h>
 #include <linux/kstrtox.h>
+#include <linux/math64.h>
 #include <linux/module.h>
+#include <linux/property.h>
 #include <linux/regulator/consumer.h>
 #include <linux/reset.h>
 #include <linux/sysfs.h>
+#include <linux/units.h>
 #include <linux/wordpart.h>
 
 #include <linux/iio/buffer.h>
@@ -41,7 +44,8 @@ static int ad5310_control_sync(struct ad5686_state *st)
 
 	return ad5686_write(st, AD5686_CMD_CONTROL_REG, 0,
 			    FIELD_PREP(AD5310_PD_MSK, pd_val & AD5686_PD_MSK) |
-			    FIELD_PREP(AD5310_REF_BIT_MSK, st->use_internal_vref ? 0 : 1));
+			    FIELD_PREP(AD5310_REF_BIT_MSK, st->use_internal_vref ? 0 : 1) |
+			    FIELD_PREP(AD5310_GAIN_BIT_MSK, st->double_scale ? 1 : 0));
 }
 
 static int ad5683_control_sync(struct ad5686_state *st)
@@ -50,7 +54,8 @@ static int ad5683_control_sync(struct ad5686_state *st)
 
 	return ad5686_write(st, AD5686_CMD_CONTROL_REG, 0,
 			    FIELD_PREP(AD5683_PD_MSK, pd_val & AD5686_PD_MSK) |
-			    FIELD_PREP(AD5683_REF_BIT_MSK, st->use_internal_vref ? 0 : 1));
+			    FIELD_PREP(AD5683_REF_BIT_MSK, st->use_internal_vref ? 0 : 1) |
+			    FIELD_PREP(AD5683_GAIN_BIT_MSK, st->double_scale ? 1 : 0));
 }
 
 static inline unsigned int ad5686_pd_mask_shift(const struct iio_chan_spec *chan)
@@ -193,9 +198,14 @@ static int ad5686_read_raw(struct iio_dev *indio_dev,
 			GENMASK(chan->scan_type.realbits - 1, 0);
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_SCALE:
-		*val = st->vref_mv;
-		*val2 = chan->scan_type.realbits;
-		return IIO_VAL_FRACTIONAL_LOG2;
+		if (st->double_scale) {
+			*val = st->scale_avail[2];
+			*val2 = st->scale_avail[3];
+		} else {
+			*val = st->scale_avail[0];
+			*val2 = st->scale_avail[1];
+		}
+		return IIO_VAL_INT_PLUS_NANO;
 	}
 	return -EINVAL;
 }
@@ -207,6 +217,8 @@ static int ad5686_write_raw(struct iio_dev *indio_dev,
 			    long mask)
 {
 	struct ad5686_state *st = iio_priv(indio_dev);
+	bool double_scale;
+	int ret;
 
 	guard(mutex)(&st->lock);
 
@@ -217,6 +229,84 @@ static int ad5686_write_raw(struct iio_dev *indio_dev,
 
 		return ad5686_write(st, AD5686_CMD_WRITE_INPUT_N_UPDATE_N,
 				    chan->address, val << chan->scan_type.shift);
+	case IIO_CHAN_INFO_SCALE:
+		if (val == st->scale_avail[0] && val2 == st->scale_avail[1])
+			double_scale = false;
+		else if (val == st->scale_avail[2] && val2 == st->scale_avail[3])
+			double_scale = true;
+		else
+			return -EINVAL;
+
+		if (st->double_scale == double_scale)
+			return 0; /* no change */
+
+		st->double_scale = double_scale;
+		switch (st->chip_info->regmap_type) {
+		case AD5310_REGMAP:
+			ret = ad5310_control_sync(st);
+			break;
+		case AD5683_REGMAP:
+			ret = ad5683_control_sync(st);
+			break;
+		case AD5686_REGMAP:
+			if (!st->gain_gpio) {
+				ret = -EINVAL;
+				break;
+			}
+
+			ret = gpiod_set_value_cansleep(st->gain_gpio,
+						       st->double_scale ? 1 : 0);
+			break;
+		default:
+			ret = -EINVAL;
+		}
+		if (ret)
+			st->double_scale = !double_scale; /* revert on failure */
+		return ret;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int ad5686_write_raw_get_fmt(struct iio_dev *indio_dev,
+				    struct iio_chan_spec const *chan,
+				    long mask)
+{
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		return IIO_VAL_INT_PLUS_NANO;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int ad5686_read_avail(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan,
+			     const int **vals, int *type, int *length,
+			     long mask)
+{
+	struct ad5686_state *st = iio_priv(indio_dev);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_SCALE:
+		*type = IIO_VAL_INT_PLUS_NANO;
+
+		if (st->chip_info->regmap_type == AD5686_REGMAP && !st->gain_gpio) {
+			/*
+			 * GAIN pin is board-strapped, so only the current
+			 * scale is available.
+			 */
+			*vals = st->double_scale ? &st->scale_avail[2] :
+						   &st->scale_avail[0];
+			*length = 2;
+			return IIO_AVAIL_LIST;
+		}
+
+		*vals = st->scale_avail;
+		*length = ARRAY_SIZE(st->scale_avail);
+		return IIO_AVAIL_LIST;
 	default:
 		return -EINVAL;
 	}
@@ -225,6 +315,8 @@ static int ad5686_write_raw(struct iio_dev *indio_dev,
 static const struct iio_info ad5686_info = {
 	.read_raw = ad5686_read_raw,
 	.write_raw = ad5686_write_raw,
+	.write_raw_get_fmt = ad5686_write_raw_get_fmt,
+	.read_avail = ad5686_read_avail,
 };
 
 static const struct iio_chan_spec_ext_info ad5686_ext_info[] = {
@@ -246,6 +338,7 @@ static const struct iio_chan_spec_ext_info ad5686_ext_info[] = {
 		.channel = chan,				\
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),	\
 		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),\
+		.info_mask_shared_by_type_available = BIT(IIO_CHAN_INFO_SCALE),\
 		.address = addr,				\
 		.scan_index = chan,				\
 		.scan_type = {					\
@@ -472,6 +565,15 @@ const struct ad5686_chip_info ad5679r_chip_info = {
 };
 EXPORT_SYMBOL_NS_GPL(ad5679r_chip_info, "IIO_AD5686");
 
+static void ad5686_init_scale_avail(struct ad5686_state *st)
+{
+	int realbits = st->chip_info->channels[0].scan_type.realbits;
+	s64 tmp = 2ULL * st->vref_mv * NANO >> realbits;
+
+	st->scale_avail[2] = div_s64_rem(tmp, NANO, &st->scale_avail[3]);
+	st->scale_avail[0] = div_s64_rem(tmp >> 1, NANO, &st->scale_avail[1]);
+}
+
 static irqreturn_t ad5686_trigger_handler(int irq, void *p)
 {
 	struct iio_poll_func *pf = p;
@@ -585,6 +687,16 @@ int ad5686_probe(struct device *dev,
 		return dev_err_probe(dev, PTR_ERR(st->ldac_gpio),
 				     "Failed to get LDAC GPIO\n");
 
+	st->double_scale = device_property_read_bool(dev, "adi,range-double");
+	st->gain_gpio = devm_gpiod_get_optional(dev, "gain",
+						st->double_scale ? GPIOD_OUT_HIGH :
+								   GPIOD_OUT_LOW);
+	if (IS_ERR(st->gain_gpio))
+		return dev_err_probe(dev, PTR_ERR(st->gain_gpio),
+				     "Failed to get GAIN GPIO\n");
+
+	ad5686_init_scale_avail(st);
+
 	/* Initialize masks to all ones */
 	st->pwr_down_mask = ~0;
 	st->pwr_down_mode = ~0;
diff --git a/drivers/iio/dac/ad5686.h b/drivers/iio/dac/ad5686.h
index cb884334e94a..92012e1be48f 100644
--- a/drivers/iio/dac/ad5686.h
+++ b/drivers/iio/dac/ad5686.h
@@ -39,9 +39,11 @@
 #define AD5686_CMD_CONTROL_REG			0x4
 #define AD5686_CMD_READBACK_ENABLE_V2		0x5
 
+#define AD5310_GAIN_BIT_MSK			BIT(7)
 #define AD5310_REF_BIT_MSK			BIT(8)
 #define AD5310_PD_MSK				GENMASK(10, 9)
 
+#define AD5683_GAIN_BIT_MSK			BIT(11)
 #define AD5683_REF_BIT_MSK			BIT(12)
 #define AD5683_PD_MSK				GENMASK(14, 13)
 
@@ -125,9 +127,12 @@ extern const struct ad5686_chip_info ad5679r_chip_info;
  * @chip_info:		chip model specific constants, available modes etc
  * @ops:		bus specific operations
  * @ldac_gpio:		LDAC pin GPIO descriptor
- * @vref_mv:		actual reference voltage used
+ * @gain_gpio:		GAIN pin GPIO descriptor
  * @pwr_down_mask:	power down mask
  * @pwr_down_mode:	current power down mode
+ * @scale_avail:	pre-calculated available scale values
+ * @vref_mv:		actual reference voltage used
+ * @double_scale:	flag to indicate the gain multiplier is applied
  * @use_internal_vref:	set to true if the internal reference voltage is used
  * @lock:		lock to protect access to state fields, which includes
  *			the data buffer during regmap ops
@@ -139,9 +144,12 @@ struct ad5686_state {
 	const struct ad5686_chip_info	*chip_info;
 	const struct ad5686_bus_ops	*ops;
 	struct gpio_desc		*ldac_gpio;
-	unsigned short			vref_mv;
+	struct gpio_desc		*gain_gpio;
 	unsigned int			pwr_down_mask;
 	unsigned int			pwr_down_mode;
+	int				scale_avail[4];
+	unsigned short			vref_mv;
+	bool				double_scale;
 	bool				use_internal_vref;
 	struct mutex			lock;
 	void				*bus_data;

-- 
2.43.0

Re: [PATCH v4 06/12] iio: dac: ad5686: consume optional reset signal

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Medium] Missing power-up/reset recovery delay after reset deassertion.
- [Medium] Ignored return values from reset control operations.
--

commit 6b4f1604bc9722fb4790d1198babf7ca8eb4d482
Author: Rodrigo Alencar <rodrigo.alencar@analog.com>

iio: dac: ad5686: consume optional reset signal

This commit adds support for an optional reset control in the probe
function. It manually generates a reset pulse after the device is
powered up.

> diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
> --- a/drivers/iio/dac/ad5686.c
> +++ b/drivers/iio/dac/ad5686.c
[ ... ]
> @@ -509,6 +516,11 @@ int ad5686_probe(struct device *dev,
>  	/* 4.5us power-up time: Datasheet Table 4: Timing Characteristics */
>  	fsleep(5);
>  
> +	/* 1us >> 30ns reset pulse activation time: Datasheet Table 4 */
> +	reset_control_assert(rstc);
> +	fsleep(1);
> +	reset_control_deassert(rstc);

[Severity: Medium]
Should we check the return values of reset_control_assert() and
reset_control_deassert() here?

If the reset controller is backed by a fallible bus (such as an I2C or
SPI GPIO expander), these calls can fail. If deassertion fails and the
return value is ignored, the driver might proceed while the hardware
is still stuck in reset, causing subsequent bus communications to silently
fail.

[Severity: Medium]
Does the hardware require a stabilization delay after the reset line is
deasserted before we start communicating with it?

Similar to the 4.5us power-up time handled above, if the device needs
recovery time after a hardware reset, proceeding immediately to the
initialization and first register writes might result in corrupted or
dropped commands.

> +
>  	/* Initialize masks to all ones */
>  	st->pwr_down_mask = ~0;
>  	st->pwr_down_mode = ~0;

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260623-ad5686-new-features-v4-0-28962a57db0f@analog.com?part=6

Re: [PATCH v4 04/12] dt-bindings: iio: dac: ad5686: rework on power supplies

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] The dt-binding makes `vdd-supply`, `vlogic-supply`, and conditionally `vref-supply` strictly required, which breaks schema validation for existing device trees.
--

commit 91cd8407525317fa145de80deea6f4d2c2d3a4d3
Author: Rodrigo Alencar <rodrigo.alencar@analog.com>
dt-bindings: iio: dac: ad5686: rework on power supplies

This commit updates the AD5686 binding to add vdd, vlogic, and vref power
supplies. It also deprecates the misleading vcc-supply property in favor of
vref-supply.

> diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5686.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5686.yaml
> index d781baca6a6c2..02e8c78e36d3d 100644
> --- a/Documentation/devicetree/bindings/iio/dac/adi,ad5686.yaml
> +++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5686.yaml

[ ... ]

> @@ -60,9 +74,23 @@ properties:
>  required:
>    - compatible
>    - reg
> +  - vdd-supply
> +  - vlogic-supply

[Severity: Medium]
Does adding vdd-supply and vlogic-supply to the unconditional required list
break dtbs_check for older device trees?

Since existing unmodified device trees lack these newly introduced supplies,
making them strictly required violates device tree backward compatibility.
While the driver handles missing supplies via dummy regulators, the schema
will flag older device trees as invalid.

>  
>  allOf:
>    - $ref: /schemas/spi/spi-peripheral-props.yaml#
> +  - if:
> +      properties:
> +        compatible:
> +          contains:
> +            enum:
> +              - adi,ad5676
> +              - adi,ad5683
> +              - adi,ad5684
> +              - adi,ad5686
> +    then:
> +      required:
> +        - vref-supply

[Severity: Medium]
Will this conditional block cause validation failures for legacy device trees
that define the previously valid vcc-supply instead of vref-supply?

The driver code continues to support the deprecated vcc-supply for backward
compatibility, but this schema update does not mirror that logic. Could this
use an anyOf block to allow either vref-supply or vcc-supply to satisfy the
reference voltage requirement for these chips?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260623-ad5686-new-features-v4-0-28962a57db0f@analog.com?part=4

Re: [PATCH v4 01/12] dt-bindings: iio: dac: ad5696: add reset/ldac/gain support

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] The `allOf` conditional block fails to restrict `gain-gpios` for all applicable devices that lack a GAIN pin.
--

commit 23c63e7ff1a35cdc5b325bc954025b5cf88c49f5
Author: Rodrigo Alencar <rodrigo.alencar@analog.com>
dt-bindings: iio: dac: ad5696: add reset/ldac/gain support

This commit adds optional GPIO properties for the RESET, LDAC, and GAIN
pins to the AD5696 device tree binding. It also includes an if-then block
to restrict the use of the gain-gpios property on devices that do not
support it.

> diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml
> --- a/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml
> +++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml
[ ... ]
> +allOf:
> +  - if:
> +      properties:
> +        compatible:
> +          contains:
> +            enum:
> +              - adi,ad5311r
> +              - adi,ad5691r
> +              - adi,ad5692r
> +              - adi,ad5693
> +              - adi,ad5693r

[Severity: Medium]
Should the 8-pin dual-channel DACs adi,ad5337r and adi,ad5338r be included
in this enum as well? 

If these hardware variants also lack a GAIN pin, omitting them from this
restriction block would allow an invalid device tree configuration specifying
gain-gpios for an adi,ad5337r or adi,ad5338r device to silently pass
validation.

> +    then:
> +      properties:
> +        gain-gpios: false
>  
>  additionalProperties: false

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260623-ad5686-new-features-v4-0-28962a57db0f@analog.com?part=1

Re: [PATCH v4 12/12] iio: dac: ad5686: add gain control support

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] Data race in `ad5686_read_avail()` due to lockless access of `st->double_scale`, which is temporarily mutated in `ad5686_write_raw()`.
--

commit 7b5b8c7fbbe74efe7dd9f093ff8593661667e614
Author: Rodrigo Alencar <rodrigo.alencar@analog.com>

iio: dac: ad5686: add gain control support

Adds gain control support to the ad5686 driver, allowing a 2x multiplier
to be applied to the output voltage either via a dedicated GAIN pin or
a control register bit field. It exposes available scales to userspace
and adds tracking of the double scale state.

> diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
> index 4dc681eb077d6..bad214b89257f 100644
> --- a/drivers/iio/dac/ad5686.c
> +++ b/drivers/iio/dac/ad5686.c
[ ... ]
> @@ -217,6 +229,84 @@ static int ad5686_write_raw(struct iio_dev *indio_dev,
>  
>  		return ad5686_write(st, AD5686_CMD_WRITE_INPUT_N_UPDATE_N,
>  				    chan->address, val << chan->scan_type.shift);
> +	case IIO_CHAN_INFO_SCALE:
> +		if (val == st->scale_avail[0] && val2 == st->scale_avail[1])
> +			double_scale = false;
> +		else if (val == st->scale_avail[2] && val2 == st->scale_avail[3])
> +			double_scale = true;
> +		else
> +			return -EINVAL;
> +
> +		if (st->double_scale == double_scale)
> +			return 0; /* no change */
> +
> +		st->double_scale = double_scale;
> +		switch (st->chip_info->regmap_type) {
> +		case AD5310_REGMAP:
> +			ret = ad5310_control_sync(st);
> +			break;
> +		case AD5683_REGMAP:
> +			ret = ad5683_control_sync(st);
> +			break;
> +		case AD5686_REGMAP:
> +			if (!st->gain_gpio) {
> +				ret = -EINVAL;
> +				break;
> +			}
> +
> +			ret = gpiod_set_value_cansleep(st->gain_gpio,
> +						       st->double_scale ? 1 : 0);
> +			break;
> +		default:
> +			ret = -EINVAL;
> +		}
> +		if (ret)
> +			st->double_scale = !double_scale; /* revert on failure */
> +		return ret;
[ ... ]
> +static int ad5686_read_avail(struct iio_dev *indio_dev,
> +			     struct iio_chan_spec const *chan,
> +			     const int **vals, int *type, int *length,
> +			     long mask)
> +{
> +	struct ad5686_state *st = iio_priv(indio_dev);
> +
> +	switch (mask) {
> +	case IIO_CHAN_INFO_SCALE:
> +		*type = IIO_VAL_INT_PLUS_NANO;
> +
> +		if (st->chip_info->regmap_type == AD5686_REGMAP && !st->gain_gpio) {
> +			/*
> +			 * GAIN pin is board-strapped, so only the current
> +			 * scale is available.
> +			 */
> +			*vals = st->double_scale ? &st->scale_avail[2] :
> +						   &st->scale_avail[0];

[Severity: Medium]
Is there a potential data race on st->double_scale here?

In ad5686_write_raw(), st->double_scale is temporarily modified and then
reverted on failure under st->lock. However, ad5686_read_avail() accesses
st->double_scale without holding st->lock.

If a sysfs read on in_voltage_scale_available happens concurrently with a
failing sysfs write on in_voltage_scale for a board-strapped device, could
the read observe the temporary invalid state of st->double_scale before
it is reverted and returned to userspace?

> +			*length = 2;
> +			return IIO_AVAIL_LIST;
> +		}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260623-ad5686-new-features-v4-0-28962a57db0f@analog.com?part=12

Re: [PATCH v4 11/12] iio: dac: ad5686: add triggered buffer support

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] The ad5686_trigger_handler fails to convert Big Endian buffer data to native CPU endianness before passing it to the write operations, causing scrambled DAC values on Little Endian systems.
--

commit b9bb35e4f394ef5515930983f7b76ce0cae1335e
Author: Rodrigo Alencar <rodrigo.alencar@analog.com>

iio: dac: ad5686: add triggered buffer support

This commit implements a trigger handler for the AD5686 DAC driver to update 
all channels simultaneously when the LDAC GPIO is available. It also flushes 
multiple channel writes at once using the sync() operation.

> diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
> index db175e77b0b7c..4dc681eb077d6 100644
> --- a/drivers/iio/dac/ad5686.c
> +++ b/drivers/iio/dac/ad5686.c
[ ... ]
> @@ -467,6 +472,60 @@ const struct ad5686_chip_info ad5679r_chip_info = {
>  };
>  EXPORT_SYMBOL_NS_GPL(ad5679r_chip_info, "IIO_AD5686");
>  
> +static irqreturn_t ad5686_trigger_handler(int irq, void *p)
> +{
> +	struct iio_poll_func *pf = p;
> +	struct iio_dev *indio_dev = pf->indio_dev;
> +	struct iio_buffer *buffer = indio_dev->buffer;
> +	struct ad5686_state *st = iio_priv(indio_dev);
> +	u16 val[AD5686_MAX_CHANNELS] = { };
> +	unsigned int scan_count, ch, i;
> +	bool async_update;
> +	int ret;
> +	u8 cmd;
> +
> +	ret = iio_pop_from_buffer(buffer, val);
> +	if (ret) {
> +		iio_trigger_notify_done(indio_dev->trig);
> +		return IRQ_HANDLED;
> +	}
> +
> +	guard(mutex)(&st->lock);
> +
> +	scan_count = bitmap_weight(indio_dev->active_scan_mask,
> +				   iio_get_masklength(indio_dev));
> +	async_update = st->ldac_gpio && scan_count > 1;
> +	if (async_update) {
> +		/* use LDAC to update all channels simultaneously */
> +		cmd = AD5686_CMD_WRITE_INPUT_N;
> +		gpiod_set_value_cansleep(st->ldac_gpio, 0);
> +	} else {
> +		cmd = AD5686_CMD_WRITE_INPUT_N_UPDATE_N;
> +	}
> +
> +	i = 0;
> +	iio_for_each_active_channel(indio_dev, ch) {
> +		ret = st->ops->write(st, cmd, indio_dev->channels[ch].address, val[i++]);

[Severity: High]
Will this send scrambled data on Little Endian CPUs?

Since the driver declares IIO_BE, the data populated by iio_pop_from_buffer() 
into the val array is in Big Endian format. Passing val[i++] directly to 
st->ops->write() as a native u16 without using be16_to_cpu() means the bytes 
might be incorrectly byte-swapped before transmission.

> +		if (ret)
> +			break;
> +	}
> +
> +	/*
> +	 * If sync() is available, it is called here regardless of write
> +	 * failure to allow bus implementation to reset. In that case, partial
> +	 * writes are unlikely as the write operations would just queue up
> +	 * the transfers.
> +	 */
> +	if (st->ops->sync)
> +		st->ops->sync(st);
> +
> +	if (async_update)
> +		gpiod_set_value_cansleep(st->ldac_gpio, 1);
> +
> +	iio_trigger_notify_done(indio_dev->trig);
> +	return IRQ_HANDLED;
> +}
[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260623-ad5686-new-features-v4-0-28962a57db0f@analog.com?part=11

Re: [PATCH v4 02/12] dt-bindings: iio: dac: ad5696: rework on power supplies

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Medium] Unconditionally requiring new `vdd-supply` and `vlogic-supply` properties breaks validation for existing device trees.
- [Medium] Conditionally requiring `vref-supply` for `adi,ad5696` breaks schema validation for legacy device trees that use the deprecated `vcc-supply`.
--

commit 7082ab254ab9eb0509320518d5cb786825dd6cbb
Author: Rodrigo Alencar <rodrigo.alencar@analog.com>

dt-bindings: iio: dac: ad5696: rework on power supplies

This commit updates the AD5696 DAC binding to include vdd-supply,
vlogic-supply, and vref-supply, while deprecating the misleading vcc-supply.
It also updates the required property lists and conditionally requires
vref-supply for specific variants.

> diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml
> index cc343cdf6085a..e10f8596f9d3f 100644
> --- a/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml
> +++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5696.yaml

[ ... ]

> @@ -62,8 +75,21 @@ properties:
>  required:
>    - compatible
>    - reg
> +  - vdd-supply
> +  - vlogic-supply

[Severity: Medium]
Does unconditionally adding vdd-supply and vlogic-supply to the required
list break schema validation for existing device trees?

Legacy device trees that legitimately omitted these properties will now fail
schema validation during make dtbs_check.

>  
>  allOf:
> +  - if:
> +      properties:
> +        compatible:
> +          contains:
> +            enum:
> +              - adi,ad5693
> +              - adi,ad5694
> +              - adi,ad5696
> +    then:
> +      required:
> +        - vref-supply

[Severity: Medium]
Does conditionally requiring vref-supply for these compatible strings break
schema validation for legacy device trees that use the deprecated vcc-supply?

Since vcc-supply was valid under the previous schema, making vref-supply
strictly required here will cause validation failures for existing device
trees. Should the schema allow either vref-supply or the deprecated
vcc-supply to preserve DT ABI compatibility?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260623-ad5686-new-features-v4-0-28962a57db0f@analog.com?part=2