Devicetree
 help / color / mirror / Atom feed
* [PATCH v2 0/6] mfd: lm3533: convert to OF bindings, improve support
@ 2026-05-28 13:51 Svyatoslav Ryhel
  2026-05-28 13:51 ` [PATCH v2 1/6] dt-bindings: leds: Document TI LM3533 LED controller Svyatoslav Ryhel
                   ` (5 more replies)
  0 siblings, 6 replies; 16+ messages in thread
From: Svyatoslav Ryhel @ 2026-05-28 13:51 UTC (permalink / raw)
  To: Lee Jones, Daniel Thompson, Jingoo Han, Pavel Machek, Rob Herring,
	Krzysztof Kozlowski, Conor Dooley, Jonathan Cameron,
	David Lechner, Nuno Sá, Andy Shevchenko, Helge Deller,
	Svyatoslav Ryhel
  Cc: Johan Hovold, dri-devel, linux-leds, devicetree, linux-kernel,
	linux-iio, linux-fbdev

Convert LM3533 to OF bindings, add missing VIN supply, add support for
setting mapping mode and LED sources based on device tree. 

---
Changes in v2:

schema
- maximum led sources for leds set to 4
- anyOf > oneOf in ALS
- improved ALS descriptions
- adjusted example
drivers
- dropped devm convertion of irq and mfd helpers
- all als configuration moved into lm3533_als_setup
- added regulator/consumer.h
- lm3533_bl_setup set before sysfs_create_group in backlight
- added check if LVLED is valid
- LM3533_REG_OUTPUT_CONF1 > LM3533_REG_OUTPUT_CONF2 for LVLED4 and LVLED5
---

Svyatoslav Ryhel (6):
  dt-bindings: leds: Document TI LM3533 LED controller
  mfd: lm3533: Convert to use OF bindings
  mfd: lm3533: Add support for VIN power supply
  mfd: lm3533: Set DMA mask
  video: backlight: lm3533_bl: Set initial mapping mode from DT
  video: leds: backlight: lm3533: Support getting LED sources from DT

 .../leds/backlight/ti,lm3533-backlight.yaml   |  68 ++++
 .../bindings/leds/ti,lm3533-leds.yaml         |  66 ++++
 .../devicetree/bindings/leds/ti,lm3533.yaml   | 170 ++++++++++
 drivers/iio/light/lm3533-als.c                |  95 +++---
 drivers/leds/leds-lm3533.c                    | 108 +++++--
 drivers/mfd/lm3533-core.c                     | 291 +++++++-----------
 drivers/video/backlight/lm3533_bl.c           | 127 ++++++--
 include/linux/mfd/lm3533.h                    |  53 +---
 8 files changed, 653 insertions(+), 325 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/leds/backlight/ti,lm3533-backlight.yaml
 create mode 100644 Documentation/devicetree/bindings/leds/ti,lm3533-leds.yaml
 create mode 100644 Documentation/devicetree/bindings/leds/ti,lm3533.yaml

-- 
2.51.0


^ permalink raw reply	[flat|nested] 16+ messages in thread

* [PATCH v2 1/6] dt-bindings: leds: Document TI LM3533 LED controller
  2026-05-28 13:51 [PATCH v2 0/6] mfd: lm3533: convert to OF bindings, improve support Svyatoslav Ryhel
@ 2026-05-28 13:51 ` Svyatoslav Ryhel
  2026-05-28 14:08   ` sashiko-bot
  2026-05-28 14:54   ` Jonathan Cameron
  2026-05-28 13:51 ` [PATCH v2 2/6] mfd: lm3533: Convert to use OF bindings Svyatoslav Ryhel
                   ` (4 subsequent siblings)
  5 siblings, 2 replies; 16+ messages in thread
From: Svyatoslav Ryhel @ 2026-05-28 13:51 UTC (permalink / raw)
  To: Lee Jones, Daniel Thompson, Jingoo Han, Pavel Machek, Rob Herring,
	Krzysztof Kozlowski, Conor Dooley, Jonathan Cameron,
	David Lechner, Nuno Sá, Andy Shevchenko, Helge Deller,
	Svyatoslav Ryhel
  Cc: Johan Hovold, dri-devel, linux-leds, devicetree, linux-kernel,
	linux-iio, linux-fbdev

Document the LM3533 - a complete power source for backlight, keypad and
indicator LEDs in smartphone handsets. The high-voltage inductive boost
converter provides the power for two series LED strings display backlight
and keypad functions.

Signed-off-by: Svyatoslav Ryhel <clamor95@gmail.com>
---
 .../leds/backlight/ti,lm3533-backlight.yaml   |  68 +++++++
 .../bindings/leds/ti,lm3533-leds.yaml         |  66 +++++++
 .../devicetree/bindings/leds/ti,lm3533.yaml   | 170 ++++++++++++++++++
 3 files changed, 304 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/leds/backlight/ti,lm3533-backlight.yaml
 create mode 100644 Documentation/devicetree/bindings/leds/ti,lm3533-leds.yaml
 create mode 100644 Documentation/devicetree/bindings/leds/ti,lm3533.yaml

diff --git a/Documentation/devicetree/bindings/leds/backlight/ti,lm3533-backlight.yaml b/Documentation/devicetree/bindings/leds/backlight/ti,lm3533-backlight.yaml
new file mode 100644
index 000000000000..866b0fb8ed04
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/backlight/ti,lm3533-backlight.yaml
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/leds/backlight/ti,lm3533-backlight.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: TI LM3533 high voltage series LED strings
+
+description:
+  This is part of the TI LM3533 MFD device. It represents two high voltage series
+  LED strings for display backlight controlled by the TI LM3533.
+
+maintainers:
+  - Svyatoslav Ryhel <clamor95@gmail.com>
+
+allOf:
+  - $ref: /schemas/leds/backlight/common.yaml#
+
+properties:
+  compatible:
+    const: ti,lm3533-backlight
+
+  reg:
+    description: Control bank selection (0 = bank A, 1 = bank B).
+    maximum: 1
+
+  led-max-microamp:
+    description: maximum current in uA with a 800 uA step.
+    minimum: 5000
+    maximum: 29800
+    default: 5000
+
+  led-sources:
+    description: |
+      HVLED strings associated with this control bank:
+        0 - HVLED1
+        1 - HVLED2
+    minItems: 1
+    maxItems: 2
+    items:
+      maximum: 1
+
+  ti,pwm-config-mask:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: |
+      Control Bank PWM Configuration Register mask that allows to configure
+      PWM input in Zones 0-4
+      BIT(0) - PWM Input is enabled
+      BIT(1) - PWM Input is enabled in Zone 0
+      BIT(2) - PWM Input is enabled in Zone 1
+      BIT(3) - PWM Input is enabled in Zone 2
+      BIT(4) - PWM Input is enabled in Zone 3
+      BIT(5) - PWM Input is enabled in Zone 4
+
+  ti,linear-mapping-mode:
+    description:
+      Enable linear mapping mode. If disabled, then it will use exponential
+      mapping mode in which the ramp up/down appears to have a more uniform
+      transition to the human eye.
+    type: boolean
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+# see ti,lm3533.yaml for an example
diff --git a/Documentation/devicetree/bindings/leds/ti,lm3533-leds.yaml b/Documentation/devicetree/bindings/leds/ti,lm3533-leds.yaml
new file mode 100644
index 000000000000..a321926de62e
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/ti,lm3533-leds.yaml
@@ -0,0 +1,66 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/leds/ti,lm3533-leds.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: TI LM3533 low voltage control banks for individual LEDs
+
+description:
+  This is part of the TI LM3533 MFD device. It represents four low voltage
+  control banks for individual LEDs provided by the TI LM3533.
+
+maintainers:
+  - Svyatoslav Ryhel <clamor95@gmail.com>
+
+allOf:
+  - $ref: /schemas/leds/common.yaml#
+
+properties:
+  compatible:
+    const: ti,lm3533-leds
+
+  reg:
+    description:
+      Control bank selection (2 = bank C, 3 = bank D, 4 = bank E, 5 = bank F).
+    minimum: 2
+    maximum: 5
+
+  led-max-microamp:
+    description: maximum current in uA with a 800 uA step.
+    minimum: 5000
+    maximum: 29800
+    default: 5000
+
+  led-sources:
+    description: |
+      LVLED associated with this control bank. May be more than 1 source per bank.
+        0 - LVLED1
+        1 - LVLED2
+        2 - LVLED3
+        3 - LVLED4
+        4 - LVLED5
+    minItems: 1
+    maxItems: 5
+    items:
+      maximum: 4
+
+  ti,pwm-config-mask:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: |
+      Control Bank PWM Configuration Register mask that allows to configure
+      PWM input in Zones 0-4
+      BIT(0) - PWM Input is enabled
+      BIT(1) - PWM Input is enabled in Zone 0
+      BIT(2) - PWM Input is enabled in Zone 1
+      BIT(3) - PWM Input is enabled in Zone 2
+      BIT(4) - PWM Input is enabled in Zone 3
+      BIT(5) - PWM Input is enabled in Zone 4
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+# see ti,lm3533.yaml for an example
diff --git a/Documentation/devicetree/bindings/leds/ti,lm3533.yaml b/Documentation/devicetree/bindings/leds/ti,lm3533.yaml
new file mode 100644
index 000000000000..6e12e12be08e
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/ti,lm3533.yaml
@@ -0,0 +1,170 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/leds/ti,lm3533.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: TI LM3533 Complete Lighting Power Solution
+
+description: >
+  The LM3533 is a complete power source for backlight, keypad, and indicator LEDs
+  in smartphone handsets. The high-voltage inductive boost converter provides the
+  power for two high voltage series LED strings for display backlight and four low
+  voltage control banks for individual LEDs. Additionally, LM3533 features an
+  interface for an external light sensor.
+
+  https://www.ti.com/product/LM3533
+
+maintainers:
+  - Svyatoslav Ryhel <clamor95@gmail.com>
+
+properties:
+  compatible:
+    const: ti,lm3533
+
+  reg:
+    maxItems: 1
+
+  enable-gpios:
+    description: GPIO connected to the HWEN pin.
+    maxItems: 1
+
+  vin-supply:
+    description: Supply connected to the IN line (2.7 V to 5.5 V).
+
+  '#address-cells':
+    const: 1
+
+  '#size-cells':
+    const: 0
+
+  ti,boost-ovp-microvolt:
+    description: boost OVP select (16V, 24V, 32V, 40V)
+    enum: [ 16000000, 24000000, 32000000, 40000000 ]
+    default: 16000000
+
+  ti,boost-freq-hz:
+    description: boost frequency select (500KHz or 1MHz)
+    enum: [ 500000, 1000000 ]
+    default: 500000
+
+  light-sensor:
+    type: object
+    additionalProperties: false
+
+    properties:
+      compatible:
+        const: ti,lm3533-als
+
+      interrupts:
+        maxItems: 1
+
+      ti,resistor-ohm:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        description:
+          Internal configuration resister value when light sensor is in
+          Analog Sensor mode and PWM mode is disabled. The expectation is
+          the input is a current from the external analog light sensor and
+          this is used to convert it to a voltage within the target range.
+        minimum: 1575
+        maximum: 200000
+
+      ti,pwm-mode:
+        type: boolean
+        description:
+          Switch for mode in which light sensor interface is running. If
+          this property is set then the light sensor interface is running
+          in PWM mode, internal resistor value is set to high-impedance (0)
+          and ti,resistor-ohm property is ignored.
+
+    required:
+      - compatible
+
+    oneOf:
+      - required:
+          - ti,resistor-ohm
+      - required:
+          - ti,pwm-mode
+
+patternProperties:
+  "^backlight@[01]$":
+    $ref: /schemas/leds/backlight/ti,lm3533-backlight.yaml#
+
+  "^led@[2-5]$":
+    $ref: /schemas/leds/ti,lm3533-leds.yaml#
+
+required:
+  - compatible
+  - reg
+  - '#address-cells'
+  - '#size-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        led-controller@36 {
+            compatible = "ti,lm3533";
+            reg = <0x36>;
+
+            enable-gpios = <&gpio 110 GPIO_ACTIVE_HIGH>;
+            vin-supply = <&vdd_3v3_bat>;
+
+            ti,boost-ovp-microvolt = <24000000>;
+            ti,boost-freq-hz = <500000>;
+
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            backlight@0 {
+                compatible = "ti,lm3533-backlight";
+                reg = <0>;
+
+                default-brightness = <113>;
+
+                led-max-microamp = <23400>;
+                led-sources = <0 1>;
+            };
+
+            led@2 {
+                compatible = "ti,lm3533-leds";
+                reg = <2>;
+
+                led-max-microamp = <23400>;
+                led-sources = <0 1>;
+            };
+
+            led@4 {
+                compatible = "ti,lm3533-leds";
+                reg = <4>;
+
+                led-max-microamp = <23400>;
+                led-sources = <2>;
+            };
+
+            led@5 {
+                compatible = "ti,lm3533-leds";
+                reg = <5>;
+
+                led-max-microamp = <23400>;
+                led-sources = <3 4>;
+            };
+
+            light-sensor {
+                compatible = "ti,lm3533-als";
+
+                interrupt-parent = <&gpio>;
+                interrupts = <80 IRQ_TYPE_LEVEL_LOW>;
+
+                ti,pwm-mode;
+            };
+        };
+    };
+...
-- 
2.51.0


^ permalink raw reply related	[flat|nested] 16+ messages in thread

* [PATCH v2 2/6] mfd: lm3533: Convert to use OF bindings
  2026-05-28 13:51 [PATCH v2 0/6] mfd: lm3533: convert to OF bindings, improve support Svyatoslav Ryhel
  2026-05-28 13:51 ` [PATCH v2 1/6] dt-bindings: leds: Document TI LM3533 LED controller Svyatoslav Ryhel
@ 2026-05-28 13:51 ` Svyatoslav Ryhel
  2026-05-28 14:37   ` sashiko-bot
  2026-05-28 14:50   ` Jonathan Cameron
  2026-05-28 13:51 ` [PATCH v2 3/6] mfd: lm3533: Add support for VIN power supply Svyatoslav Ryhel
                   ` (3 subsequent siblings)
  5 siblings, 2 replies; 16+ messages in thread
From: Svyatoslav Ryhel @ 2026-05-28 13:51 UTC (permalink / raw)
  To: Lee Jones, Daniel Thompson, Jingoo Han, Pavel Machek, Rob Herring,
	Krzysztof Kozlowski, Conor Dooley, Jonathan Cameron,
	David Lechner, Nuno Sá, Andy Shevchenko, Helge Deller,
	Svyatoslav Ryhel
  Cc: Johan Hovold, dri-devel, linux-leds, devicetree, linux-kernel,
	linux-iio, linux-fbdev

Since there are no users of this driver via platform data, remove the
platform data support and switch to using Device Tree bindings.
Additionally, optimize functions used only by platform data.

Signed-off-by: Svyatoslav Ryhel <clamor95@gmail.com>
---
 drivers/iio/light/lm3533-als.c      |  95 ++++------
 drivers/leds/leds-lm3533.c          |  51 ++++--
 drivers/mfd/lm3533-core.c           | 268 ++++++++++------------------
 drivers/video/backlight/lm3533_bl.c |  52 ++++--
 include/linux/mfd/lm3533.h          |  51 +-----
 5 files changed, 212 insertions(+), 305 deletions(-)

diff --git a/drivers/iio/light/lm3533-als.c b/drivers/iio/light/lm3533-als.c
index 99f0b903018c..cbd337b73bd9 100644
--- a/drivers/iio/light/lm3533-als.c
+++ b/drivers/iio/light/lm3533-als.c
@@ -16,15 +16,18 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/mfd/core.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/units.h>
 
 #include <linux/mfd/lm3533.h>
 
 
-#define LM3533_ALS_RESISTOR_MIN			1
-#define LM3533_ALS_RESISTOR_MAX			127
+#define LM3533_ALS_RESISTOR_MIN			1575
+#define LM3533_ALS_RESISTOR_MAX			200000
 #define LM3533_ALS_CHANNEL_CURRENT_MAX		2
 #define LM3533_ALS_THRESH_MAX			3
 #define LM3533_ALS_ZONE_MAX			4
@@ -56,6 +59,9 @@ struct lm3533_als {
 
 	atomic_t zone;
 	struct mutex thresh_mutex;
+
+	bool pwm_mode;
+	u32 r_select;
 };
 
 
@@ -714,59 +720,33 @@ static const struct attribute_group lm3533_als_attribute_group = {
 	.attrs = lm3533_als_attributes
 };
 
-static int lm3533_als_set_input_mode(struct lm3533_als *als, bool pwm_mode)
+static int lm3533_als_setup(struct lm3533_als *als)
 {
-	u8 mask = LM3533_ALS_INPUT_MODE_MASK;
-	u8 val;
+	struct device *dev = &als->pdev.dev;
 	int ret;
 
-	if (pwm_mode)
-		val = mask;	/* pwm input */
-	else
-		val = 0;	/* analog input */
-
-	ret = lm3533_update(als->lm3533, LM3533_REG_ALS_CONF, val, mask);
-	if (ret) {
-		dev_err(&als->pdev->dev, "failed to set input mode %d\n",
-								pwm_mode);
-		return ret;
-	}
-
-	return 0;
-}
-
-static int lm3533_als_set_resistor(struct lm3533_als *als, u8 val)
-{
-	int ret;
-
-	if (val < LM3533_ALS_RESISTOR_MIN || val > LM3533_ALS_RESISTOR_MAX) {
-		dev_err(&als->pdev->dev, "invalid resistor value\n");
-		return -EINVAL;
-	}
-
-	ret = lm3533_write(als->lm3533, LM3533_REG_ALS_RESISTOR_SELECT, val);
-	if (ret) {
-		dev_err(&als->pdev->dev, "failed to set resistor\n");
-		return ret;
-	}
+	device_property_read_u32(dev, "ti,resistor-value-ohm",
+				 &als->r_select);
 
-	return 0;
-}
+	als->r_select = clamp(als->r_select, LM3533_ALS_RESISTOR_MIN,
+			      LM3533_ALS_RESISTOR_MAX);
+	als->r_select = DIV_ROUND_UP(2 * MICRO, 10 * als->r_select);
 
-static int lm3533_als_setup(struct lm3533_als *als,
-			    const struct lm3533_als_platform_data *pdata)
-{
-	int ret;
+	als->pwm_mode = device_property_read_bool(dev, "ti,pwm-mode");
 
-	ret = lm3533_als_set_input_mode(als, pdata->pwm_mode);
+	ret = lm3533_update(lm3533, LM3533_REG_ALS_CONF, als->pwm_mode ?
+			    LM3533_ALS_INPUT_MODE_MASK : 0,
+			    LM3533_ALS_INPUT_MODE_MASK);
 	if (ret)
-		return ret;
+		return dev_err_probe(dev, ret, "failed to set input mode %d\n",
+				     als->pwm_mode);
 
 	/* ALS input is always high impedance in PWM-mode. */
-	if (!pdata->pwm_mode) {
-		ret = lm3533_als_set_resistor(als, pdata->r_select);
+	if (!als->pwm_mode) {
+		ret = lm3533_write(lm3533, LM3533_REG_ALS_RESISTOR_SELECT,
+				   (u8)als->r_select);
 		if (ret)
-			return ret;
+			return dev_err_probe(dev, ret, "failed to set resistor\n");
 	}
 
 	return 0;
@@ -828,7 +808,6 @@ static const struct iio_info lm3533_als_info = {
 
 static int lm3533_als_probe(struct platform_device *pdev)
 {
-	const struct lm3533_als_platform_data *pdata;
 	struct lm3533 *lm3533;
 	struct lm3533_als *als;
 	struct iio_dev *indio_dev;
@@ -838,12 +817,6 @@ static int lm3533_als_probe(struct platform_device *pdev)
 	if (!lm3533)
 		return -EINVAL;
 
-	pdata = dev_get_platdata(&pdev->dev);
-	if (!pdata) {
-		dev_err(&pdev->dev, "no platform data\n");
-		return -EINVAL;
-	}
-
 	indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*als));
 	if (!indio_dev)
 		return -ENOMEM;
@@ -852,25 +825,28 @@ static int lm3533_als_probe(struct platform_device *pdev)
 	indio_dev->channels = lm3533_als_channels;
 	indio_dev->num_channels = ARRAY_SIZE(lm3533_als_channels);
 	indio_dev->name = dev_name(&pdev->dev);
-	iio_device_set_parent(indio_dev, pdev->dev.parent);
 	indio_dev->modes = INDIO_DIRECT_MODE;
 
 	als = iio_priv(indio_dev);
 	als->lm3533 = lm3533;
 	als->pdev = pdev;
-	als->irq = lm3533->irq;
+	als->irq = platform_get_irq_optional(pdev, 0);
+
+	if (als->irq == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+
 	atomic_set(&als->zone, 0);
 	mutex_init(&als->thresh_mutex);
 
 	platform_set_drvdata(pdev, indio_dev);
 
-	if (als->irq) {
+	if (als->irq > 0) {
 		ret = lm3533_als_setup_irq(als, indio_dev);
 		if (ret)
 			return ret;
 	}
 
-	ret = lm3533_als_setup(als, pdata);
+	ret = lm3533_als_setup(als);
 	if (ret)
 		goto err_free_irq;
 
@@ -907,9 +883,16 @@ static void lm3533_als_remove(struct platform_device *pdev)
 		free_irq(als->irq, indio_dev);
 }
 
+static const struct of_device_id lm3533_als_match_table[] = {
+	{ .compatible = "ti,lm3533-als" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, lm3533_als_match_table);
+
 static struct platform_driver lm3533_als_driver = {
 	.driver	= {
 		.name	= "lm3533-als",
+		.of_match_table = lm3533_als_match_table,
 	},
 	.probe		= lm3533_als_probe,
 	.remove		= lm3533_als_remove,
diff --git a/drivers/leds/leds-lm3533.c b/drivers/leds/leds-lm3533.c
index 45795f2a1042..d707d43d5526 100644
--- a/drivers/leds/leds-lm3533.c
+++ b/drivers/leds/leds-lm3533.c
@@ -10,8 +10,10 @@
 #include <linux/module.h>
 #include <linux/leds.h>
 #include <linux/mfd/core.h>
+#include <linux/mod_devicetable.h>
 #include <linux/mutex.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/slab.h>
 
 #include <linux/mfd/lm3533.h>
@@ -48,6 +50,9 @@ struct lm3533_led {
 
 	struct mutex mutex;
 	unsigned long flags;
+
+	u32 max_current;
+	u32 pwm;
 };
 
 
@@ -632,22 +637,20 @@ static const struct attribute_group *lm3533_led_attribute_groups[] = {
 	NULL
 };
 
-static int lm3533_led_setup(struct lm3533_led *led,
-					struct lm3533_led_platform_data *pdata)
+static int lm3533_led_setup(struct lm3533_led *led)
 {
 	int ret;
 
-	ret = lm3533_ctrlbank_set_max_current(&led->cb, pdata->max_current);
+	ret = lm3533_ctrlbank_set_max_current(&led->cb, led->max_current);
 	if (ret)
 		return ret;
 
-	return lm3533_ctrlbank_set_pwm(&led->cb, pdata->pwm);
+	return lm3533_ctrlbank_set_pwm(&led->cb, (u8)led->pwm);
 }
 
 static int lm3533_led_probe(struct platform_device *pdev)
 {
 	struct lm3533 *lm3533;
-	struct lm3533_led_platform_data *pdata;
 	struct lm3533_led *led;
 	int ret;
 
@@ -657,12 +660,6 @@ static int lm3533_led_probe(struct platform_device *pdev)
 	if (!lm3533)
 		return -EINVAL;
 
-	pdata = dev_get_platdata(&pdev->dev);
-	if (!pdata) {
-		dev_err(&pdev->dev, "no platform data\n");
-		return -EINVAL;
-	}
-
 	if (pdev->id < 0 || pdev->id >= LM3533_LVCTRLBANK_COUNT) {
 		dev_err(&pdev->dev, "illegal LED id %d\n", pdev->id);
 		return -EINVAL;
@@ -673,8 +670,6 @@ static int lm3533_led_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	led->lm3533 = lm3533;
-	led->cdev.name = pdata->name;
-	led->cdev.default_trigger = pdata->default_trigger;
 	led->cdev.brightness_set_blocking = lm3533_led_set;
 	led->cdev.brightness_get = lm3533_led_get;
 	led->cdev.blink_set = lm3533_led_blink_set;
@@ -682,6 +677,15 @@ static int lm3533_led_probe(struct platform_device *pdev)
 	led->cdev.groups = lm3533_led_attribute_groups;
 	led->id = pdev->id;
 
+	led->cdev.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s-%d",
+					pdev->name, led->id);
+	if (!led->cdev.name)
+		return -ENOMEM;
+
+	led->cdev.default_trigger = "none";
+	device_property_read_string(&pdev->dev, "linux,default-trigger",
+				    &led->cdev.default_trigger);
+
 	mutex_init(&led->mutex);
 
 	/* The class framework makes a callback to get brightness during
@@ -694,15 +698,23 @@ static int lm3533_led_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, led);
 
-	ret = led_classdev_register(pdev->dev.parent, &led->cdev);
+	ret = led_classdev_register(&pdev->dev, &led->cdev);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register LED %d\n", pdev->id);
+		dev_err(&pdev->dev, "failed to register LED %d\n", led->id);
 		return ret;
 	}
 
 	led->cb.dev = led->cdev.dev;
 
-	ret = lm3533_led_setup(led, pdata);
+	device_property_read_u32(&pdev->dev, "led-max-microamp",
+				 &led->max_current);
+	led->max_current = clamp(led->max_current, LM3533_LED_MAX_CURRENT_MIN,
+				 LM3533_LED_MAX_CURRENT_MAX);
+
+	led->pwm = 0;
+	device_property_read_u32(&pdev->dev, "ti,pwm-config-mask", &led->pwm);
+
+	ret = lm3533_led_setup(led);
 	if (ret)
 		goto err_deregister;
 
@@ -739,9 +751,16 @@ static void lm3533_led_shutdown(struct platform_device *pdev)
 	lm3533_led_set(&led->cdev, LED_OFF);		/* disable blink */
 }
 
+static const struct of_device_id lm3533_led_match_table[] = {
+	{ .compatible = "ti,lm3533-leds" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, lm3533_led_match_table);
+
 static struct platform_driver lm3533_led_driver = {
 	.driver = {
 		.name = "lm3533-leds",
+		.of_match_table = lm3533_led_match_table,
 	},
 	.probe		= lm3533_led_probe,
 	.remove		= lm3533_led_remove,
diff --git a/drivers/mfd/lm3533-core.c b/drivers/mfd/lm3533-core.c
index 0a2409d00b2e..8495e9119871 100644
--- a/drivers/mfd/lm3533-core.c
+++ b/drivers/mfd/lm3533-core.c
@@ -14,19 +14,26 @@
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/mfd/core.h>
+#include <linux/mod_devicetable.h>
+#include <linux/property.h>
 #include <linux/regmap.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/units.h>
 
 #include <linux/mfd/lm3533.h>
 
 
 #define LM3533_BOOST_OVP_MASK		0x06
 #define LM3533_BOOST_OVP_SHIFT		1
+#define LM3533_BOOST_OVP_MIN		16000000
+#define LM3533_BOOST_OVP_MAX		40000000
 
 #define LM3533_BOOST_FREQ_MASK		0x01
 #define LM3533_BOOST_FREQ_SHIFT		0
+#define LM3533_BOOST_FREQ_MIN		500000
+#define LM3533_BOOST_FREQ_MAX		1000000
 
 #define LM3533_BL_ID_MASK		1
 #define LM3533_LED_ID_MASK		3
@@ -35,6 +42,7 @@
 
 #define LM3533_HVLED_ID_MAX		2
 #define LM3533_LVLED_ID_MAX		5
+#define LM3533_CELLS_MAX		7
 
 #define LM3533_REG_OUTPUT_CONF1		0x10
 #define LM3533_REG_OUTPUT_CONF2		0x11
@@ -42,44 +50,6 @@
 
 #define LM3533_REG_MAX			0xb2
 
-
-static struct mfd_cell lm3533_als_devs[] = {
-	{
-		.name	= "lm3533-als",
-		.id	= -1,
-	},
-};
-
-static struct mfd_cell lm3533_bl_devs[] = {
-	{
-		.name	= "lm3533-backlight",
-		.id	= 0,
-	},
-	{
-		.name	= "lm3533-backlight",
-		.id	= 1,
-	},
-};
-
-static struct mfd_cell lm3533_led_devs[] = {
-	{
-		.name	= "lm3533-leds",
-		.id	= 0,
-	},
-	{
-		.name	= "lm3533-leds",
-		.id	= 1,
-	},
-	{
-		.name	= "lm3533-leds",
-		.id	= 2,
-	},
-	{
-		.name	= "lm3533-leds",
-		.id	= 3,
-	},
-};
-
 int lm3533_read(struct lm3533 *lm3533, u8 reg, u8 *val)
 {
 	int tmp;
@@ -132,35 +102,6 @@ int lm3533_update(struct lm3533 *lm3533, u8 reg, u8 val, u8 mask)
 }
 EXPORT_SYMBOL_GPL(lm3533_update);
 
-static int lm3533_set_boost_freq(struct lm3533 *lm3533,
-						enum lm3533_boost_freq freq)
-{
-	int ret;
-
-	ret = lm3533_update(lm3533, LM3533_REG_BOOST_PWM,
-					freq << LM3533_BOOST_FREQ_SHIFT,
-					LM3533_BOOST_FREQ_MASK);
-	if (ret)
-		dev_err(lm3533->dev, "failed to set boost frequency\n");
-
-	return ret;
-}
-
-
-static int lm3533_set_boost_ovp(struct lm3533 *lm3533,
-						enum lm3533_boost_ovp ovp)
-{
-	int ret;
-
-	ret = lm3533_update(lm3533, LM3533_REG_BOOST_PWM,
-					ovp << LM3533_BOOST_OVP_SHIFT,
-					LM3533_BOOST_OVP_MASK);
-	if (ret)
-		dev_err(lm3533->dev, "failed to set boost ovp\n");
-
-	return ret;
-}
-
 /*
  * HVLED output config -- output hvled controlled by backlight bl
  */
@@ -376,135 +317,93 @@ static struct attribute_group lm3533_attribute_group = {
 	.attrs		= lm3533_attributes
 };
 
-static int lm3533_device_als_init(struct lm3533 *lm3533)
+static int lm3533_device_init(struct lm3533 *lm3533)
 {
-	struct lm3533_platform_data *pdata = dev_get_platdata(lm3533->dev);
+	struct device *dev = lm3533->dev;
+	struct mfd_cell lm3533_cells[LM3533_CELLS_MAX];
+	u32 count = 0, reg;
 	int ret;
 
-	if (!pdata->als)
-		return 0;
-
-	lm3533_als_devs[0].platform_data = pdata->als;
-	lm3533_als_devs[0].pdata_size = sizeof(*pdata->als);
-
-	ret = mfd_add_devices(lm3533->dev, 0, lm3533_als_devs, 1, NULL,
-			      0, NULL);
-	if (ret) {
-		dev_err(lm3533->dev, "failed to add ALS device\n");
-		return ret;
-	}
-
-	lm3533->have_als = 1;
-
-	return 0;
-}
+	lm3533_enable(lm3533);
 
-static int lm3533_device_bl_init(struct lm3533 *lm3533)
-{
-	struct lm3533_platform_data *pdata = dev_get_platdata(lm3533->dev);
-	int i;
-	int ret;
+	device_for_each_child_node_scoped(lm3533->dev, child) {
+		if (!fwnode_device_is_available(child))
+			continue;
 
-	if (!pdata->backlights || pdata->num_backlights == 0)
-		return 0;
+		if (count >= LM3533_CELLS_MAX)
+			break;
 
-	if (pdata->num_backlights > ARRAY_SIZE(lm3533_bl_devs))
-		pdata->num_backlights = ARRAY_SIZE(lm3533_bl_devs);
+		if (fwnode_device_is_compatible(child, "ti,lm3533-als")) {
+			lm3533_cells[count].name = "lm3533-als";
+			lm3533_cells[count].id = PLATFORM_DEVID_NONE;
+			lm3533_cells[count].of_compatible = "ti,lm3533-als";
 
-	for (i = 0; i < pdata->num_backlights; ++i) {
-		lm3533_bl_devs[i].platform_data = &pdata->backlights[i];
-		lm3533_bl_devs[i].pdata_size = sizeof(pdata->backlights[i]);
-	}
+			lm3533->have_als = true;
+		}
 
-	ret = mfd_add_devices(lm3533->dev, 0, lm3533_bl_devs,
-			      pdata->num_backlights, NULL, 0, NULL);
-	if (ret) {
-		dev_err(lm3533->dev, "failed to add backlight devices\n");
-		return ret;
-	}
+		if (fwnode_device_is_compatible(child, "ti,lm3533-backlight")) {
+			ret = fwnode_property_read_u32(child, "reg", &reg);
+			if (ret || reg > LM3533_HVLED_ID_MAX) {
+				dev_err(dev, "invalid backlight reg %d\n", reg);
+				continue;
+			}
 
-	lm3533->have_backlights = 1;
+			lm3533_cells[count].name = "lm3533-backlight";
+			lm3533_cells[count].id = reg;
+			lm3533_cells[count].of_compatible = "ti,lm3533-backlight";
 
-	return 0;
-}
+			lm3533->have_backlights = true;
+		}
 
-static int lm3533_device_led_init(struct lm3533 *lm3533)
-{
-	struct lm3533_platform_data *pdata = dev_get_platdata(lm3533->dev);
-	int i;
-	int ret;
+		if (fwnode_device_is_compatible(child, "ti,lm3533-leds")) {
+			ret = fwnode_property_read_u32(child, "reg", &reg);
+			if (ret || reg < LM3533_HVLED_ID_MAX ||
+			    reg > LM3533_LVLED_ID_MAX) {
+				dev_err(dev, "invalid LED reg %d\n", reg);
+				continue;
+			}
 
-	if (!pdata->leds || pdata->num_leds == 0)
-		return 0;
+			lm3533_cells[count].name = "lm3533-leds";
+			lm3533_cells[count].id = reg - LM3533_HVLED_ID_MAX;
+			lm3533_cells[count].of_compatible = "ti,lm3533-leds";
 
-	if (pdata->num_leds > ARRAY_SIZE(lm3533_led_devs))
-		pdata->num_leds = ARRAY_SIZE(lm3533_led_devs);
+			lm3533->have_leds = true;
+		}
 
-	for (i = 0; i < pdata->num_leds; ++i) {
-		lm3533_led_devs[i].platform_data = &pdata->leds[i];
-		lm3533_led_devs[i].pdata_size = sizeof(pdata->leds[i]);
+		count++;
 	}
 
-	ret = mfd_add_devices(lm3533->dev, 0, lm3533_led_devs,
-			      pdata->num_leds, NULL, 0, NULL);
+	ret = lm3533_update(lm3533, LM3533_REG_BOOST_PWM,
+			    lm3533->boost_freq << LM3533_BOOST_FREQ_SHIFT,
+			    LM3533_BOOST_FREQ_MASK);
 	if (ret) {
-		dev_err(lm3533->dev, "failed to add LED devices\n");
-		return ret;
+		dev_err(dev, "failed to set boost frequency\n");
+		goto err_disable;
 	}
 
-	lm3533->have_leds = 1;
-
-	return 0;
-}
-
-static int lm3533_device_setup(struct lm3533 *lm3533,
-					struct lm3533_platform_data *pdata)
-{
-	int ret;
-
-	ret = lm3533_set_boost_freq(lm3533, pdata->boost_freq);
-	if (ret)
-		return ret;
-
-	return lm3533_set_boost_ovp(lm3533, pdata->boost_ovp);
-}
-
-static int lm3533_device_init(struct lm3533 *lm3533)
-{
-	struct lm3533_platform_data *pdata = dev_get_platdata(lm3533->dev);
-	int ret;
-
-	dev_dbg(lm3533->dev, "%s\n", __func__);
-
-	if (!pdata) {
-		dev_err(lm3533->dev, "no platform data\n");
-		return -EINVAL;
+	ret = lm3533_update(lm3533, LM3533_REG_BOOST_PWM,
+			    lm3533->boost_ovp << LM3533_BOOST_OVP_SHIFT,
+			    LM3533_BOOST_OVP_MASK);
+	if (ret) {
+		dev_err(dev, "failed to set boost ovp\n");
+		goto err_disable;
 	}
 
-	lm3533->hwen = devm_gpiod_get(lm3533->dev, NULL, GPIOD_OUT_LOW);
-	if (IS_ERR(lm3533->hwen))
-		return dev_err_probe(lm3533->dev, PTR_ERR(lm3533->hwen), "failed to request HWEN GPIO\n");
-	gpiod_set_consumer_name(lm3533->hwen, "lm3533-hwen");
-
-	lm3533_enable(lm3533);
-
-	ret = lm3533_device_setup(lm3533, pdata);
-	if (ret)
+	ret = mfd_add_devices(dev, 0, lm3533_cells, count, NULL, 0, NULL);
+	if (ret) {
+		dev_err(dev, "failed to add MFD devices: %d\n", ret);
 		goto err_disable;
+	}
 
-	lm3533_device_als_init(lm3533);
-	lm3533_device_bl_init(lm3533);
-	lm3533_device_led_init(lm3533);
-
-	ret = sysfs_create_group(&lm3533->dev->kobj, &lm3533_attribute_group);
-	if (ret < 0) {
-		dev_err(lm3533->dev, "failed to create sysfs attributes\n");
-		goto err_unregister;
+	ret = sysfs_create_group(&dev->kobj, &lm3533_attribute_group);
+	if (ret) {
+		dev_err(dev, "failed to create sysfs attributes\n");
+		goto err_remove_devices;
 	}
 
 	return 0;
 
-err_unregister:
+err_remove_devices:
 	mfd_remove_devices(lm3533->dev);
 err_disable:
 	lm3533_disable(lm3533);
@@ -517,8 +416,6 @@ static void lm3533_device_exit(struct lm3533 *lm3533)
 	dev_dbg(lm3533->dev, "%s\n", __func__);
 
 	sysfs_remove_group(&lm3533->dev->kobj, &lm3533_attribute_group);
-
-	mfd_remove_devices(lm3533->dev);
 	lm3533_disable(lm3533);
 }
 
@@ -589,7 +486,26 @@ static int lm3533_i2c_probe(struct i2c_client *i2c)
 		return PTR_ERR(lm3533->regmap);
 
 	lm3533->dev = &i2c->dev;
-	lm3533->irq = i2c->irq;
+
+	lm3533->hwen = devm_gpiod_get_optional(lm3533->dev, "enable",
+					       GPIOD_OUT_LOW);
+	if (IS_ERR(lm3533->hwen))
+		return dev_err_probe(lm3533->dev, PTR_ERR(lm3533->hwen),
+				     "failed to get HWEN GPIO\n");
+
+	device_property_read_u32(lm3533->dev, "ti,boost-ovp-microvolt",
+				 &lm3533->boost_ovp);
+
+	lm3533->boost_ovp = clamp(lm3533->boost_ovp, LM3533_BOOST_OVP_MIN,
+				  LM3533_BOOST_OVP_MAX);
+	lm3533->boost_ovp = lm3533->boost_ovp / (8 * MICRO) - 2;
+
+	device_property_read_u32(lm3533->dev, "ti,boost-freq-hz",
+				 &lm3533->boost_freq);
+
+	lm3533->boost_freq = clamp(lm3533->boost_freq, LM3533_BOOST_FREQ_MIN,
+				   LM3533_BOOST_FREQ_MAX);
+	lm3533->boost_freq = lm3533->boost_freq / (500 * KILO) - 1;
 
 	return lm3533_device_init(lm3533);
 }
@@ -600,9 +516,16 @@ static void lm3533_i2c_remove(struct i2c_client *i2c)
 
 	dev_dbg(&i2c->dev, "%s\n", __func__);
 
+	mfd_remove_devices(lm3533->dev);
 	lm3533_device_exit(lm3533);
 }
 
+static const struct of_device_id lm3533_match_table[] = {
+	{ .compatible = "ti,lm3533" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, lm3533_match_table);
+
 static const struct i2c_device_id lm3533_i2c_ids[] = {
 	{ "lm3533" },
 	{ }
@@ -612,6 +535,7 @@ MODULE_DEVICE_TABLE(i2c, lm3533_i2c_ids);
 static struct i2c_driver lm3533_i2c_driver = {
 	.driver = {
 		   .name = "lm3533",
+		   .of_match_table = lm3533_match_table,
 	},
 	.id_table	= lm3533_i2c_ids,
 	.probe		= lm3533_i2c_probe,
diff --git a/drivers/video/backlight/lm3533_bl.c b/drivers/video/backlight/lm3533_bl.c
index babfd3ceec86..42da652df58d 100644
--- a/drivers/video/backlight/lm3533_bl.c
+++ b/drivers/video/backlight/lm3533_bl.c
@@ -9,7 +9,9 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/backlight.h>
 #include <linux/slab.h>
 
@@ -27,6 +29,9 @@ struct lm3533_bl {
 	struct lm3533_ctrlbank cb;
 	struct backlight_device *bd;
 	int id;
+
+	u32 max_current;
+	u32 pwm;
 };
 
 
@@ -246,25 +251,24 @@ static struct attribute_group lm3533_bl_attribute_group = {
 	.attrs		= lm3533_bl_attributes
 };
 
-static int lm3533_bl_setup(struct lm3533_bl *bl,
-					struct lm3533_bl_platform_data *pdata)
+static int lm3533_bl_setup(struct lm3533_bl *bl)
 {
 	int ret;
 
-	ret = lm3533_ctrlbank_set_max_current(&bl->cb, pdata->max_current);
+	ret = lm3533_ctrlbank_set_max_current(&bl->cb, bl->max_current);
 	if (ret)
 		return ret;
 
-	return lm3533_ctrlbank_set_pwm(&bl->cb, pdata->pwm);
+	return lm3533_ctrlbank_set_pwm(&bl->cb, bl->pwm);
 }
 
 static int lm3533_bl_probe(struct platform_device *pdev)
 {
 	struct lm3533 *lm3533;
-	struct lm3533_bl_platform_data *pdata;
 	struct lm3533_bl *bl;
 	struct backlight_device *bd;
 	struct backlight_properties props;
+	char *name = NULL;
 	int ret;
 
 	dev_dbg(&pdev->dev, "%s\n", __func__);
@@ -273,12 +277,6 @@ static int lm3533_bl_probe(struct platform_device *pdev)
 	if (!lm3533)
 		return -EINVAL;
 
-	pdata = dev_get_platdata(&pdev->dev);
-	if (!pdata) {
-		dev_err(&pdev->dev, "no platform data\n");
-		return -EINVAL;
-	}
-
 	if (pdev->id < 0 || pdev->id >= LM3533_HVCTRLBANK_COUNT) {
 		dev_err(&pdev->dev, "illegal backlight id %d\n", pdev->id);
 		return -EINVAL;
@@ -295,13 +293,20 @@ static int lm3533_bl_probe(struct platform_device *pdev)
 	bl->cb.id = lm3533_bl_get_ctrlbank_id(bl);
 	bl->cb.dev = NULL;			/* until registered */
 
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s-%d",
+			      pdev->name, pdev->id);
+	if (!name)
+		return -ENOMEM;
+
 	memset(&props, 0, sizeof(props));
 	props.type = BACKLIGHT_RAW;
 	props.max_brightness = LM3533_BL_MAX_BRIGHTNESS;
-	props.brightness = pdata->default_brightness;
-	bd = devm_backlight_device_register(&pdev->dev, pdata->name,
-					pdev->dev.parent, bl, &lm3533_bl_ops,
-					&props);
+	props.brightness = LM3533_BL_MAX_BRIGHTNESS;
+	device_property_read_u32(&pdev->dev, "default-brightness",
+				 &props.brightness);
+
+	bd = devm_backlight_device_register(&pdev->dev, name, &pdev->dev,
+					    bl, &lm3533_bl_ops, &props);
 	if (IS_ERR(bd)) {
 		dev_err(&pdev->dev, "failed to register backlight device\n");
 		return PTR_ERR(bd);
@@ -320,7 +325,15 @@ static int lm3533_bl_probe(struct platform_device *pdev)
 
 	backlight_update_status(bd);
 
-	ret = lm3533_bl_setup(bl, pdata);
+	device_property_read_u32(&pdev->dev, "led-max-microamp",
+				 &bl->max_current);
+	bl->max_current = clamp(bl->max_current, LM3533_LED_MAX_CURRENT_MIN,
+				LM3533_LED_MAX_CURRENT_MAX);
+
+	bl->pwm = 0;
+	device_property_read_u32(&pdev->dev, "ti,pwm-config-mask", &bl->pwm);
+
+	ret = lm3533_bl_setup(bl);
 	if (ret)
 		goto err_sysfs_remove;
 
@@ -381,10 +394,17 @@ static void lm3533_bl_shutdown(struct platform_device *pdev)
 	lm3533_ctrlbank_disable(&bl->cb);
 }
 
+static const struct of_device_id lm3533_bl_match_table[] = {
+	{ .compatible = "ti,lm3533-backlight" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, lm3533_bl_match_table);
+
 static struct platform_driver lm3533_bl_driver = {
 	.driver = {
 		.name	= "lm3533-backlight",
 		.pm	= &lm3533_bl_pm_ops,
+		.of_match_table = lm3533_bl_match_table,
 	},
 	.probe		= lm3533_bl_probe,
 	.remove		= lm3533_bl_remove,
diff --git a/include/linux/mfd/lm3533.h b/include/linux/mfd/lm3533.h
index 69059a7a2ce5..3aa962d4c747 100644
--- a/include/linux/mfd/lm3533.h
+++ b/include/linux/mfd/lm3533.h
@@ -15,6 +15,9 @@
 #define LM3533_ATTR_RW(_name) \
 	DEVICE_ATTR(_name, S_IRUGO | S_IWUSR , show_##_name, store_##_name)
 
+#define LM3533_LED_MAX_CURRENT_MIN	5000
+#define LM3533_LED_MAX_CURRENT_MAX	29800
+
 struct device;
 struct gpio_desc;
 struct regmap;
@@ -25,7 +28,9 @@ struct lm3533 {
 	struct regmap *regmap;
 
 	struct gpio_desc *hwen;
-	int irq;
+
+	u32 boost_ovp;
+	u32 boost_freq;
 
 	unsigned have_als:1;
 	unsigned have_backlights:1;
@@ -38,50 +43,6 @@ struct lm3533_ctrlbank {
 	int id;
 };
 
-struct lm3533_als_platform_data {
-	unsigned pwm_mode:1;		/* PWM input mode (default analog) */
-	u8 r_select;			/* 1 - 127 (ignored in PWM-mode) */
-};
-
-struct lm3533_bl_platform_data {
-	char *name;
-	u16 max_current;		/* 5000 - 29800 uA (800 uA step) */
-	u8 default_brightness;		/* 0 - 255 */
-	u8 pwm;				/* 0 - 0x3f */
-};
-
-struct lm3533_led_platform_data {
-	char *name;
-	const char *default_trigger;
-	u16 max_current;		/* 5000 - 29800 uA (800 uA step) */
-	u8 pwm;				/* 0 - 0x3f */
-};
-
-enum lm3533_boost_freq {
-	LM3533_BOOST_FREQ_500KHZ,
-	LM3533_BOOST_FREQ_1000KHZ,
-};
-
-enum lm3533_boost_ovp {
-	LM3533_BOOST_OVP_16V,
-	LM3533_BOOST_OVP_24V,
-	LM3533_BOOST_OVP_32V,
-	LM3533_BOOST_OVP_40V,
-};
-
-struct lm3533_platform_data {
-	enum lm3533_boost_ovp boost_ovp;
-	enum lm3533_boost_freq boost_freq;
-
-	struct lm3533_als_platform_data *als;
-
-	struct lm3533_bl_platform_data *backlights;
-	int num_backlights;
-
-	struct lm3533_led_platform_data *leds;
-	int num_leds;
-};
-
 extern int lm3533_ctrlbank_enable(struct lm3533_ctrlbank *cb);
 extern int lm3533_ctrlbank_disable(struct lm3533_ctrlbank *cb);
 
-- 
2.51.0


^ permalink raw reply related	[flat|nested] 16+ messages in thread

* [PATCH v2 3/6] mfd: lm3533: Add support for VIN power supply
  2026-05-28 13:51 [PATCH v2 0/6] mfd: lm3533: convert to OF bindings, improve support Svyatoslav Ryhel
  2026-05-28 13:51 ` [PATCH v2 1/6] dt-bindings: leds: Document TI LM3533 LED controller Svyatoslav Ryhel
  2026-05-28 13:51 ` [PATCH v2 2/6] mfd: lm3533: Convert to use OF bindings Svyatoslav Ryhel
@ 2026-05-28 13:51 ` Svyatoslav Ryhel
  2026-05-28 14:56   ` sashiko-bot
  2026-05-28 13:51 ` [PATCH v2 4/6] mfd: lm3533: Set DMA mask Svyatoslav Ryhel
                   ` (2 subsequent siblings)
  5 siblings, 1 reply; 16+ messages in thread
From: Svyatoslav Ryhel @ 2026-05-28 13:51 UTC (permalink / raw)
  To: Lee Jones, Daniel Thompson, Jingoo Han, Pavel Machek, Rob Herring,
	Krzysztof Kozlowski, Conor Dooley, Jonathan Cameron,
	David Lechner, Nuno Sá, Andy Shevchenko, Helge Deller,
	Svyatoslav Ryhel
  Cc: Johan Hovold, dri-devel, linux-leds, devicetree, linux-kernel,
	linux-iio, linux-fbdev

Add support for 2.7V-5.5V VIN power supply.

Signed-off-by: Svyatoslav Ryhel <clamor95@gmail.com>
---
 drivers/mfd/lm3533-core.c  | 23 +++++++++++++++++++++--
 include/linux/mfd/lm3533.h |  2 ++
 2 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/mfd/lm3533-core.c b/drivers/mfd/lm3533-core.c
index 8495e9119871..519f8c16a3f3 100644
--- a/drivers/mfd/lm3533-core.c
+++ b/drivers/mfd/lm3533-core.c
@@ -17,6 +17,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/property.h>
 #include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
@@ -164,14 +165,25 @@ static int lm3533_set_lvled_config(struct lm3533 *lm3533, u8 lvled, u8 led)
 	return ret;
 }
 
-static void lm3533_enable(struct lm3533 *lm3533)
+static int lm3533_enable(struct lm3533 *lm3533)
 {
+	int ret;
+
+	ret = regulator_enable(lm3533->vin_supply);
+	if (ret) {
+		dev_err(lm3533->dev, "failed to enable vin power supply\n");
+		return ret;
+	}
+
 	gpiod_set_value(lm3533->hwen, 1);
+
+	return 0;
 }
 
 static void lm3533_disable(struct lm3533 *lm3533)
 {
 	gpiod_set_value(lm3533->hwen, 0);
+	regulator_disable(lm3533->vin_supply);
 }
 
 enum lm3533_attribute_type {
@@ -324,7 +336,9 @@ static int lm3533_device_init(struct lm3533 *lm3533)
 	u32 count = 0, reg;
 	int ret;
 
-	lm3533_enable(lm3533);
+	ret = lm3533_enable(lm3533);
+	if (ret)
+		return ret;
 
 	device_for_each_child_node_scoped(lm3533->dev, child) {
 		if (!fwnode_device_is_available(child))
@@ -493,6 +507,11 @@ static int lm3533_i2c_probe(struct i2c_client *i2c)
 		return dev_err_probe(lm3533->dev, PTR_ERR(lm3533->hwen),
 				     "failed to get HWEN GPIO\n");
 
+	lm3533->vin_supply = devm_regulator_get(lm3533->dev, "vin");
+	if (IS_ERR(lm3533->vin_supply))
+		return dev_err_probe(lm3533->dev, PTR_ERR(lm3533->vin_supply),
+				     "failed to get vin-supply\n");
+
 	device_property_read_u32(lm3533->dev, "ti,boost-ovp-microvolt",
 				 &lm3533->boost_ovp);
 
diff --git a/include/linux/mfd/lm3533.h b/include/linux/mfd/lm3533.h
index 3aa962d4c747..d751773fc92d 100644
--- a/include/linux/mfd/lm3533.h
+++ b/include/linux/mfd/lm3533.h
@@ -21,6 +21,7 @@
 struct device;
 struct gpio_desc;
 struct regmap;
+struct regulator;
 
 struct lm3533 {
 	struct device *dev;
@@ -28,6 +29,7 @@ struct lm3533 {
 	struct regmap *regmap;
 
 	struct gpio_desc *hwen;
+	struct regulator *vin_supply;
 
 	u32 boost_ovp;
 	u32 boost_freq;
-- 
2.51.0


^ permalink raw reply related	[flat|nested] 16+ messages in thread

* [PATCH v2 4/6] mfd: lm3533: Set DMA mask
  2026-05-28 13:51 [PATCH v2 0/6] mfd: lm3533: convert to OF bindings, improve support Svyatoslav Ryhel
                   ` (2 preceding siblings ...)
  2026-05-28 13:51 ` [PATCH v2 3/6] mfd: lm3533: Add support for VIN power supply Svyatoslav Ryhel
@ 2026-05-28 13:51 ` Svyatoslav Ryhel
  2026-05-28 15:28   ` sashiko-bot
  2026-05-28 13:51 ` [PATCH v2 5/6] video: backlight: lm3533_bl: Set initial mapping mode from DT Svyatoslav Ryhel
  2026-05-28 13:51 ` [PATCH v2 6/6] video: leds: backlight: lm3533: Support getting LED sources " Svyatoslav Ryhel
  5 siblings, 1 reply; 16+ messages in thread
From: Svyatoslav Ryhel @ 2026-05-28 13:51 UTC (permalink / raw)
  To: Lee Jones, Daniel Thompson, Jingoo Han, Pavel Machek, Rob Herring,
	Krzysztof Kozlowski, Conor Dooley, Jonathan Cameron,
	David Lechner, Nuno Sá, Andy Shevchenko, Helge Deller,
	Svyatoslav Ryhel
  Cc: Johan Hovold, dri-devel, linux-leds, devicetree, linux-kernel,
	linux-iio, linux-fbdev

Missing coherent_dma_mask assigning triggers the following warning in
dmesg:

[    3.287872] platform lm3533-backlight.0: DMA mask not set

Since this warning might be elevated to an error in the future, set
coherent_dma_mask to zero because both the core and cells do not utilize
DMA.

Signed-off-by: Svyatoslav Ryhel <clamor95@gmail.com>
---
 drivers/mfd/lm3533-core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/mfd/lm3533-core.c b/drivers/mfd/lm3533-core.c
index 519f8c16a3f3..3cfdebf5fb52 100644
--- a/drivers/mfd/lm3533-core.c
+++ b/drivers/mfd/lm3533-core.c
@@ -526,6 +526,10 @@ static int lm3533_i2c_probe(struct i2c_client *i2c)
 				   LM3533_BOOST_FREQ_MAX);
 	lm3533->boost_freq = lm3533->boost_freq / (500 * KILO) - 1;
 
+	/* LM3533 and child devices do not use DMA */
+	i2c->dev.coherent_dma_mask = 0;
+	i2c->dev.dma_mask = &i2c->dev.coherent_dma_mask;
+
 	return lm3533_device_init(lm3533);
 }
 
-- 
2.51.0


^ permalink raw reply related	[flat|nested] 16+ messages in thread

* [PATCH v2 5/6] video: backlight: lm3533_bl: Set initial mapping mode from DT
  2026-05-28 13:51 [PATCH v2 0/6] mfd: lm3533: convert to OF bindings, improve support Svyatoslav Ryhel
                   ` (3 preceding siblings ...)
  2026-05-28 13:51 ` [PATCH v2 4/6] mfd: lm3533: Set DMA mask Svyatoslav Ryhel
@ 2026-05-28 13:51 ` Svyatoslav Ryhel
  2026-05-28 16:00   ` sashiko-bot
  2026-05-28 13:51 ` [PATCH v2 6/6] video: leds: backlight: lm3533: Support getting LED sources " Svyatoslav Ryhel
  5 siblings, 1 reply; 16+ messages in thread
From: Svyatoslav Ryhel @ 2026-05-28 13:51 UTC (permalink / raw)
  To: Lee Jones, Daniel Thompson, Jingoo Han, Pavel Machek, Rob Herring,
	Krzysztof Kozlowski, Conor Dooley, Jonathan Cameron,
	David Lechner, Nuno Sá, Andy Shevchenko, Helge Deller,
	Svyatoslav Ryhel
  Cc: Johan Hovold, dri-devel, linux-leds, devicetree, linux-kernel,
	linux-iio, linux-fbdev

Add support to obtain the initial mapping mode from DT instead of leaving
it unconfigured. Additionally, update the linear sysfs code, which uses a
similar coding pattern.

Signed-off-by: Svyatoslav Ryhel <clamor95@gmail.com>
---
 drivers/video/backlight/lm3533_bl.c | 50 ++++++++++++++++-------------
 1 file changed, 27 insertions(+), 23 deletions(-)

diff --git a/drivers/video/backlight/lm3533_bl.c b/drivers/video/backlight/lm3533_bl.c
index 42da652df58d..c03d0d1667e4 100644
--- a/drivers/video/backlight/lm3533_bl.c
+++ b/drivers/video/backlight/lm3533_bl.c
@@ -22,6 +22,7 @@
 #define LM3533_BL_MAX_BRIGHTNESS	255
 
 #define LM3533_REG_CTRLBANK_AB_BCONF	0x1a
+#define   CTRLBANK_AB_BCONF_MODE(n)	BIT(2 * (n) + 1)
 
 
 struct lm3533_bl {
@@ -32,6 +33,7 @@ struct lm3533_bl {
 
 	u32 max_current;
 	u32 pwm;
+	bool linear;
 };
 
 
@@ -135,8 +137,9 @@ static ssize_t show_linear(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	struct lm3533_bl *bl = dev_get_drvdata(dev);
+	int id = lm3533_bl_get_ctrlbank_id(bl);
+	u8 mask = CTRLBANK_AB_BCONF_MODE(id);
 	u8 val;
-	u8 mask;
 	int linear;
 	int ret;
 
@@ -144,8 +147,6 @@ static ssize_t show_linear(struct device *dev,
 	if (ret)
 		return ret;
 
-	mask = 1 << (2 * lm3533_bl_get_ctrlbank_id(bl) + 1);
-
 	if (val & mask)
 		linear = 1;
 	else
@@ -159,23 +160,16 @@ static ssize_t store_linear(struct device *dev,
 					const char *buf, size_t len)
 {
 	struct lm3533_bl *bl = dev_get_drvdata(dev);
+	int id = lm3533_bl_get_ctrlbank_id(bl);
 	unsigned long linear;
-	u8 mask;
-	u8 val;
 	int ret;
 
 	if (kstrtoul(buf, 0, &linear))
 		return -EINVAL;
 
-	mask = 1 << (2 * lm3533_bl_get_ctrlbank_id(bl) + 1);
-
-	if (linear)
-		val = mask;
-	else
-		val = 0;
-
-	ret = lm3533_update(bl->lm3533, LM3533_REG_CTRLBANK_AB_BCONF, val,
-									mask);
+	ret = lm3533_update(bl->lm3533, LM3533_REG_CTRLBANK_AB_BCONF,
+			    linear ? CTRLBANK_AB_BCONF_MODE(id) : 0,
+			    CTRLBANK_AB_BCONF_MODE(id));
 	if (ret)
 		return ret;
 
@@ -253,8 +247,15 @@ static struct attribute_group lm3533_bl_attribute_group = {
 
 static int lm3533_bl_setup(struct lm3533_bl *bl)
 {
+	int id = lm3533_bl_get_ctrlbank_id(bl);
 	int ret;
 
+	ret = lm3533_update(bl->lm3533, LM3533_REG_CTRLBANK_AB_BCONF,
+			    bl->linear ? CTRLBANK_AB_BCONF_MODE(id) : 0,
+			    CTRLBANK_AB_BCONF_MODE(id));
+	if (ret)
+		return ret;
+
 	ret = lm3533_ctrlbank_set_max_current(&bl->cb, bl->max_current);
 	if (ret)
 		return ret;
@@ -317,14 +318,6 @@ static int lm3533_bl_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, bl);
 
-	ret = sysfs_create_group(&bd->dev.kobj, &lm3533_bl_attribute_group);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to create sysfs attributes\n");
-		return ret;
-	}
-
-	backlight_update_status(bd);
-
 	device_property_read_u32(&pdev->dev, "led-max-microamp",
 				 &bl->max_current);
 	bl->max_current = clamp(bl->max_current, LM3533_LED_MAX_CURRENT_MIN,
@@ -333,9 +326,20 @@ static int lm3533_bl_probe(struct platform_device *pdev)
 	bl->pwm = 0;
 	device_property_read_u32(&pdev->dev, "ti,pwm-config-mask", &bl->pwm);
 
+	bl->linear = device_property_read_bool(&pdev->dev,
+					       "ti,linear-mapping-mode");
+
 	ret = lm3533_bl_setup(bl);
 	if (ret)
-		goto err_sysfs_remove;
+		return ret;
+
+	ret = sysfs_create_group(&bd->dev.kobj, &lm3533_bl_attribute_group);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to create sysfs attributes\n");
+		return ret;
+	}
+
+	backlight_update_status(bd);
 
 	ret = lm3533_ctrlbank_enable(&bl->cb);
 	if (ret)
-- 
2.51.0


^ permalink raw reply related	[flat|nested] 16+ messages in thread

* [PATCH v2 6/6] video: leds: backlight: lm3533: Support getting LED sources from DT
  2026-05-28 13:51 [PATCH v2 0/6] mfd: lm3533: convert to OF bindings, improve support Svyatoslav Ryhel
                   ` (4 preceding siblings ...)
  2026-05-28 13:51 ` [PATCH v2 5/6] video: backlight: lm3533_bl: Set initial mapping mode from DT Svyatoslav Ryhel
@ 2026-05-28 13:51 ` Svyatoslav Ryhel
  2026-05-28 16:33   ` sashiko-bot
  5 siblings, 1 reply; 16+ messages in thread
From: Svyatoslav Ryhel @ 2026-05-28 13:51 UTC (permalink / raw)
  To: Lee Jones, Daniel Thompson, Jingoo Han, Pavel Machek, Rob Herring,
	Krzysztof Kozlowski, Conor Dooley, Jonathan Cameron,
	David Lechner, Nuno Sá, Andy Shevchenko, Helge Deller,
	Svyatoslav Ryhel
  Cc: Johan Hovold, dri-devel, linux-leds, devicetree, linux-kernel,
	linux-iio, linux-fbdev

Add Control Bank to HVLED/LVLED muxing support based on the led-sources
defined in the device tree.

Signed-off-by: Svyatoslav Ryhel <clamor95@gmail.com>
---
 drivers/leds/leds-lm3533.c          | 55 ++++++++++++++++++++++++++++-
 drivers/video/backlight/lm3533_bl.c | 37 ++++++++++++++++++-
 2 files changed, 90 insertions(+), 2 deletions(-)

diff --git a/drivers/leds/leds-lm3533.c b/drivers/leds/leds-lm3533.c
index d707d43d5526..07390bba9a48 100644
--- a/drivers/leds/leds-lm3533.c
+++ b/drivers/leds/leds-lm3533.c
@@ -7,6 +7,7 @@
  * Author: Johan Hovold <jhovold@gmail.com>
  */
 
+#include <linux/bits.h>
 #include <linux/module.h>
 #include <linux/leds.h>
 #include <linux/mfd/core.h>
@@ -26,6 +27,12 @@
 #define LM3533_ALS_CHANNEL_LV_MIN	1
 #define LM3533_ALS_CHANNEL_LV_MAX	2
 
+#define LM3533_REG_OUTPUT_CONF1			0x10
+#define   OUTPUT_CONF1_MASK			GENMASK(7, 2)
+#define   OUTPUT_CONF1_SHIFT			2
+#define LM3533_REG_OUTPUT_CONF2			0x11
+#define   OUTPUT_CONF2_MASK			GENMASK(3, 0)
+#define   OUTPUT_CONF2_SHIFT			6
 #define LM3533_REG_CTRLBANK_BCONF_BASE		0x1b
 #define LM3533_REG_PATTERN_ENABLE		0x28
 #define LM3533_REG_PATTERN_LOW_TIME_BASE	0x71
@@ -53,6 +60,9 @@ struct lm3533_led {
 
 	u32 max_current;
 	u32 pwm;
+
+	int num_leds;
+	u32 leds[LM3533_LVCTRLBANK_MAX];
 };
 
 
@@ -639,7 +649,33 @@ static const struct attribute_group *lm3533_led_attribute_groups[] = {
 
 static int lm3533_led_setup(struct lm3533_led *led)
 {
-	int ret;
+	u32 output_cfg_shift = 0;
+	u32 output_cfg_val = 0;
+	int ret, i;
+
+	if (led->num_leds) {
+		for (i = 0; i < led->num_leds; i++) {
+			if (led->leds[i] > LM3533_LVCTRLBANK_MAX)
+				continue;
+
+			output_cfg_shift = led->leds[i] * 2;
+			output_cfg_val |= led->id << output_cfg_shift;
+		}
+
+		/* LVLED1, LVLED2 and LVLED3 */
+		ret = lm3533_update(led->lm3533, LM3533_REG_OUTPUT_CONF1,
+				    output_cfg_val << OUTPUT_CONF1_SHIFT,
+				    OUTPUT_CONF1_MASK);
+		if (ret)
+			return ret;
+
+		/* LVLED4 and LVLED5 */
+		ret = lm3533_update(led->lm3533, LM3533_REG_OUTPUT_CONF2,
+				    output_cfg_val >> OUTPUT_CONF2_SHIFT,
+				    OUTPUT_CONF2_MASK);
+		if (ret)
+			return ret;
+	}
 
 	ret = lm3533_ctrlbank_set_max_current(&led->cb, led->max_current);
 	if (ret)
@@ -714,6 +750,23 @@ static int lm3533_led_probe(struct platform_device *pdev)
 	led->pwm = 0;
 	device_property_read_u32(&pdev->dev, "ti,pwm-config-mask", &led->pwm);
 
+	led->num_leds = device_property_count_u32(&pdev->dev, "led-sources");
+
+	/*
+	 * If led-sources property is not set then either this Control Bank uses
+	 * its default LVLED or is not linked to any LVLED at all.
+	 */
+	if (led->num_leds > 0 && led->num_leds <= LM3533_LVCTRLBANK_MAX) {
+		ret = device_property_read_u32_array(&pdev->dev, "led-sources",
+						     led->leds, led->num_leds);
+		if (ret) {
+			dev_err(&pdev->dev, "failed to get led-sources\n");
+			goto err_deregister;
+		}
+	} else {
+		led->num_leds = 0;
+	}
+
 	ret = lm3533_led_setup(led);
 	if (ret)
 		goto err_deregister;
diff --git a/drivers/video/backlight/lm3533_bl.c b/drivers/video/backlight/lm3533_bl.c
index c03d0d1667e4..82b46a531dd2 100644
--- a/drivers/video/backlight/lm3533_bl.c
+++ b/drivers/video/backlight/lm3533_bl.c
@@ -7,6 +7,7 @@
  * Author: Johan Hovold <jhovold@gmail.com>
  */
 
+#include <linux/bits.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/mod_devicetable.h>
@@ -21,6 +22,8 @@
 #define LM3533_HVCTRLBANK_COUNT		2
 #define LM3533_BL_MAX_BRIGHTNESS	255
 
+#define LM3533_REG_OUTPUT_CONF1		0x10
+#define   OUTPUT_CONF1_MASK		GENMASK(1, 0)
 #define LM3533_REG_CTRLBANK_AB_BCONF	0x1a
 #define   CTRLBANK_AB_BCONF_MODE(n)	BIT(2 * (n) + 1)
 
@@ -34,6 +37,9 @@ struct lm3533_bl {
 	u32 max_current;
 	u32 pwm;
 	bool linear;
+
+	u32 num_leds;
+	u32 led_strings[LM3533_HVCTRLBANK_COUNT];
 };
 
 
@@ -248,7 +254,8 @@ static struct attribute_group lm3533_bl_attribute_group = {
 static int lm3533_bl_setup(struct lm3533_bl *bl)
 {
 	int id = lm3533_bl_get_ctrlbank_id(bl);
-	int ret;
+	u32 output_cfg_val = 0;
+	int ret, i;
 
 	ret = lm3533_update(bl->lm3533, LM3533_REG_CTRLBANK_AB_BCONF,
 			    bl->linear ? CTRLBANK_AB_BCONF_MODE(id) : 0,
@@ -256,6 +263,16 @@ static int lm3533_bl_setup(struct lm3533_bl *bl)
 	if (ret)
 		return ret;
 
+	if (bl->num_leds) {
+		for (i = 0; i < bl->num_leds; i++)
+			output_cfg_val |= id << bl->led_strings[i];
+
+		ret = lm3533_update(bl->lm3533, LM3533_REG_OUTPUT_CONF1,
+				    output_cfg_val, OUTPUT_CONF1_MASK);
+		if (ret)
+			return ret;
+	}
+
 	ret = lm3533_ctrlbank_set_max_current(&bl->cb, bl->max_current);
 	if (ret)
 		return ret;
@@ -329,6 +346,24 @@ static int lm3533_bl_probe(struct platform_device *pdev)
 	bl->linear = device_property_read_bool(&pdev->dev,
 					       "ti,linear-mapping-mode");
 
+	bl->num_leds = device_property_count_u32(&pdev->dev, "led-sources");
+
+	/*
+	 * If led-sources property is not set then either this Control Bank uses
+	 * its default HVLED or is not linked to any HVLED at all.
+	 */
+	if (bl->num_leds > 0 && bl->num_leds <= LM3533_HVCTRLBANK_COUNT) {
+		ret = device_property_read_u32_array(&pdev->dev, "led-sources",
+						     bl->led_strings,
+						     bl->num_leds);
+		if (ret) {
+			dev_err(&pdev->dev, "failed to get led-sources\n");
+			goto err_sysfs_remove;
+		}
+	} else {
+		bl->num_leds = 0;
+	}
+
 	ret = lm3533_bl_setup(bl);
 	if (ret)
 		return ret;
-- 
2.51.0


^ permalink raw reply related	[flat|nested] 16+ messages in thread

* Re: [PATCH v2 1/6] dt-bindings: leds: Document TI LM3533 LED controller
  2026-05-28 13:51 ` [PATCH v2 1/6] dt-bindings: leds: Document TI LM3533 LED controller Svyatoslav Ryhel
@ 2026-05-28 14:08   ` sashiko-bot
  2026-05-28 14:54   ` Jonathan Cameron
  1 sibling, 0 replies; 16+ messages in thread
From: sashiko-bot @ 2026-05-28 14:08 UTC (permalink / raw)
  To: Svyatoslav Ryhel; +Cc: devicetree, robh, conor+dt

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] The property `ti,resistor-ohm` does not use the standard DT schema unit suffix (`-ohms`), and its description contains a typo ('resister').
--

commit 3710ffb632b560bb2fb8a924f794c4e747f0362b
Author: Svyatoslav Ryhel <clamor95@gmail.com>

dt-bindings: leds: Document TI LM3533 LED controller

This commit documents the LM3533, a complete power source for backlight, keypad,
and indicator LEDs in smartphone handsets. The high-voltage inductive boost
converter provides power for two series LED strings for the display backlight
and keypad functions.

> diff --git a/Documentation/devicetree/bindings/leds/ti,lm3533.yaml b/Documentation/devicetree/bindings/leds/ti,lm3533.yaml
> new file mode 100644
> index 0000000000000..6e12e12be08e5
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/leds/ti,lm3533.yaml
> @@ -0,0 +1,170 @@
[ ... ]
> +  light-sensor:
> +    type: object
> +    additionalProperties: false
> +
> +    properties:
> +      compatible:
> +        const: ti,lm3533-als
> +
> +      interrupts:
> +        maxItems: 1
> +
> +      ti,resistor-ohm:
> +        $ref: /schemas/types.yaml#/definitions/uint32
> +        description:
> +          Internal configuration resister value when light sensor is in

[Severity: Low]
This isn't a bug, but should this property use the standard dt-schema unit
suffix -ohms instead of -ohm? Standardizing the unit suffix allows
dt-schema to automatically infer the property type without needing an
explicit reference.

Additionally, is there a typo in the description where it says resister
instead of resistor?

> +          Analog Sensor mode and PWM mode is disabled. The expectation is
> +          the input is a current from the external analog light sensor and
> +          this is used to convert it to a voltage within the target range.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260528135123.103745-1-clamor95@gmail.com?part=1

^ permalink raw reply	[flat|nested] 16+ messages in thread

* Re: [PATCH v2 2/6] mfd: lm3533: Convert to use OF bindings
  2026-05-28 13:51 ` [PATCH v2 2/6] mfd: lm3533: Convert to use OF bindings Svyatoslav Ryhel
@ 2026-05-28 14:37   ` sashiko-bot
  2026-05-28 14:50   ` Jonathan Cameron
  1 sibling, 0 replies; 16+ messages in thread
From: sashiko-bot @ 2026-05-28 14:37 UTC (permalink / raw)
  To: Svyatoslav Ryhel; +Cc: devicetree, robh, conor+dt

Thank you for your contribution! Sashiko AI review found 7 potential issue(s) to consider:
- [High] The `lm3533_cells` array is allocated on the stack but never zero-initialized, causing it to contain random garbage data.
- [High] The cell iterator logic increments the `count` variable for every child node unconditionally, even if the node does not match any expected compatible strings.
- [Medium] The ALS driver attempts to free an invalid IRQ number on error paths and during device removal when no IRQ is present.
- [Medium] Uninitialized stack memory is printed to the kernel log if `fwnode_property_read_u32()` fails to read the "reg" property.
- [Low] The patch introduces basic syntax and scoping errors in `lm3533_als_setup()` that completely prevent compilation.
- [Low] The backlight device tree `reg` property is validated against the wrong maximum limit in the MFD core.
- [Low] Passing an `int *` to a function expecting a `u32 *` causes compiler warnings/errors and breaks the build.
--

commit 9af50d17aae60cc268d70b24e00ddaa3a0500388
Author: Svyatoslav Ryhel <clamor95@gmail.com>

mfd: lm3533: Convert to use OF bindings

Since there are no users of this driver via platform data, remove the
platform data support and switch to using Device Tree bindings.
Additionally, optimize functions used only by platform data.

> diff --git a/drivers/iio/light/lm3533-als.c b/drivers/iio/light/lm3533-als.c
> index 99f0b903018cf..cbd337b73bd9f 100644
> --- a/drivers/iio/light/lm3533-als.c
> +++ b/drivers/iio/light/lm3533-als.c

[ ... ]

> @@ -714,59 +720,33 @@ static const struct attribute_group lm3533_als_attribute_group = {
>  	.attrs = lm3533_als_attributes
>  };
>  
> -static int lm3533_als_set_input_mode(struct lm3533_als *als, bool pwm_mode)
> +static int lm3533_als_setup(struct lm3533_als *als)
>  {
> -	u8 mask = LM3533_ALS_INPUT_MODE_MASK;
> -	u8 val;
> +	struct device *dev = &als->pdev.dev;

[Severity: Low]
Does this syntax cause a build error? The pointer als->pdev requires
the -> operator to access dev, like &als->pdev->dev.

>  	int ret;
>  
> -	if (pwm_mode)
> -		val = mask;	/* pwm input */
> -	else
> -		val = 0;	/* analog input */
> -
> -	ret = lm3533_update(als->lm3533, LM3533_REG_ALS_CONF, val, mask);
> -	if (ret) {
> -		dev_err(&als->pdev->dev, "failed to set input mode %d\n",
> -								pwm_mode);
> -		return ret;
> -	}
> -
> -	return 0;
> -}
> -
> -static int lm3533_als_set_resistor(struct lm3533_als *als, u8 val)
> -{
> -	int ret;
> -
> -	if (val < LM3533_ALS_RESISTOR_MIN || val > LM3533_ALS_RESISTOR_MAX) {
> -		dev_err(&als->pdev->dev, "invalid resistor value\n");
> -		return -EINVAL;
> -	}
> -
> -	ret = lm3533_write(als->lm3533, LM3533_REG_ALS_RESISTOR_SELECT, val);
> -	if (ret) {
> -		dev_err(&als->pdev->dev, "failed to set resistor\n");
> -		return ret;
> -	}
> +	device_property_read_u32(dev, "ti,resistor-value-ohm",
> +				 &als->r_select);
>  
> -	return 0;
> -}
> +	als->r_select = clamp(als->r_select, LM3533_ALS_RESISTOR_MIN,
> +			      LM3533_ALS_RESISTOR_MAX);
> +	als->r_select = DIV_ROUND_UP(2 * MICRO, 10 * als->r_select);
>  
> -static int lm3533_als_setup(struct lm3533_als *als,
> -			    const struct lm3533_als_platform_data *pdata)
> -{
> -	int ret;
> +	als->pwm_mode = device_property_read_bool(dev, "ti,pwm-mode");
>  
> -	ret = lm3533_als_set_input_mode(als, pdata->pwm_mode);
> +	ret = lm3533_update(lm3533, LM3533_REG_ALS_CONF, als->pwm_mode ?

[Severity: Low]
Will this fail to compile since lm3533 is undeclared in this scope? It
appears this should use als->lm3533 instead.

[ ... ]

> @@ -838,12 +817,6 @@ static int lm3533_als_probe(struct platform_device *pdev)
>  	if (!lm3533)
>  		return -EINVAL;
>  
> -	pdata = dev_get_platdata(&pdev->dev);
> -	if (!pdata) {
> -		dev_err(&pdev->dev, "no platform data\n");
> -		return -EINVAL;
> -	}
> -
>  	indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*als));
>  	if (!indio_dev)
>  		return -ENOMEM;
> @@ -852,25 +825,28 @@ static int lm3533_als_probe(struct platform_device *pdev)
>  	indio_dev->channels = lm3533_als_channels;
>  	indio_dev->num_channels = ARRAY_SIZE(lm3533_als_channels);
>  	indio_dev->name = dev_name(&pdev->dev);
> -	iio_device_set_parent(indio_dev, pdev->dev.parent);
>  	indio_dev->modes = INDIO_DIRECT_MODE;
>  
>  	als = iio_priv(indio_dev);
>  	als->lm3533 = lm3533;
>  	als->pdev = pdev;
> -	als->irq = lm3533->irq;
> +	als->irq = platform_get_irq_optional(pdev, 0);

[Severity: Medium]
Will this cause problems during error handling or device removal?
platform_get_irq_optional() returns negative error codes when no IRQ
is present. The existing cleanup paths check if (als->irq) which evaluates
to true for negative numbers, causing it to call free_irq() with an
invalid IRQ number. Should the cleanup checks be updated to
if (als->irq > 0)?

[ ... ]

> diff --git a/drivers/mfd/lm3533-core.c b/drivers/mfd/lm3533-core.c
> index 0a2409d00b2e0..8495e91198711 100644
> --- a/drivers/mfd/lm3533-core.c
> +++ b/drivers/mfd/lm3533-core.c

[ ... ]

> -static int lm3533_device_init(struct lm3533 *lm3533)
> +static int lm3533_device_init(struct lm3533 *lm3533)
>  {
> -	struct lm3533_platform_data *pdata = dev_get_platdata(lm3533->dev);
> +	struct device *dev = lm3533->dev;
> +	struct mfd_cell lm3533_cells[LM3533_CELLS_MAX];

[Severity: High]
Does this array need to be zero-initialized? Because it's allocated on
the stack, fields like num_resources and resources will contain garbage
memory. When mfd_add_devices() processes it, could this lead to wild
pointer dereferences?

> +	u32 count = 0, reg;
>  	int ret;
>  
> -	dev_dbg(lm3533->dev, "%s\n", __func__);
> -
> -	if (!pdata) {
> -		dev_err(lm3533->dev, "no platform data\n");
> -		return -EINVAL;
> +	lm3533_enable(lm3533);
>  
> -	lm3533->hwen = devm_gpiod_get(lm3533->dev, NULL, GPIOD_OUT_LOW);
> -	if (IS_ERR(lm3533->hwen))
> -		return dev_err_probe(lm3533->dev, PTR_ERR(lm3533->hwen), "failed to request HWEN GPIO\n");
> -	gpiod_set_consumer_name(lm3533->hwen, "lm3533-hwen");
> -
> -	lm3533_enable(lm3533);
> -
> -	ret = lm3533_device_setup(lm3533, pdata);
> -	if (ret)
> +	device_for_each_child_node_scoped(lm3533->dev, child) {
> +		if (!fwnode_device_is_available(child))
> +			continue;
>  
> -	lm3533_device_als_init(lm3533);
> -	lm3533_device_bl_init(lm3533);
> -	lm3533_device_led_init(lm3533);
> -
> -	ret = sysfs_create_group(&lm3533->dev->kobj, &lm3533_attribute_group);
> -	if (ret < 0) {
> -		dev_err(lm3533->dev, "failed to create sysfs attributes\n");
> -		goto err_unregister;
> +		if (count >= LM3533_CELLS_MAX)
> +			break;
>  
> +		if (fwnode_device_is_compatible(child, "ti,lm3533-als")) {
> +			lm3533_cells[count].name = "lm3533-als";
> +			lm3533_cells[count].id = PLATFORM_DEVID_NONE;
> +			lm3533_cells[count].of_compatible = "ti,lm3533-als";
>  
> +			lm3533->have_als = true;
> +		}
>  
> +		if (fwnode_device_is_compatible(child, "ti,lm3533-backlight")) {
> +			ret = fwnode_property_read_u32(child, "reg", &reg);
> +			if (ret || reg > LM3533_HVLED_ID_MAX) {

[Severity: Low]
Is LM3533_HVLED_ID_MAX the correct boundary to check here? The backlight IDs
should typically be validated against LM3533_BL_ID_MAX. Since
LM3533_HVLED_ID_MAX is 2, it would allow invalid backlight IDs to bypass
this check.

> +				dev_err(dev, "invalid backlight reg %d\n", reg);

[Severity: Medium]
If fwnode_property_read_u32() returns an error, reg remains uninitialized.
Could this print stack garbage memory to the kernel log?

> +				continue;
> +			}
>  
> +			lm3533_cells[count].name = "lm3533-backlight";
> +			lm3533_cells[count].id = reg;
> +			lm3533_cells[count].of_compatible = "ti,lm3533-backlight";
>  
> +			lm3533->have_backlights = true;
> +		}
>  
> +		if (fwnode_device_is_compatible(child, "ti,lm3533-leds")) {
> +			ret = fwnode_property_read_u32(child, "reg", &reg);
> +			if (ret || reg < LM3533_HVLED_ID_MAX ||
> +			    reg > LM3533_LVLED_ID_MAX) {
> +				dev_err(dev, "invalid LED reg %d\n", reg);
> +				continue;
> +			}
>  
> +			lm3533_cells[count].name = "lm3533-leds";
> +			lm3533_cells[count].id = reg - LM3533_HVLED_ID_MAX;
> +			lm3533_cells[count].of_compatible = "ti,lm3533-leds";
>  
> +			lm3533->have_leds = true;
> +		}
>  
> +		count++;

[Severity: High]
Does count increment unconditionally even if the child node didn't match
any of the compatible strings? If an unrelated child node is present, it
would increment count while leaving the lm3533_cells[count] entirely
unpopulated. When mfd_add_devices() is called, this could result in a NULL
pointer dereference on the .name field.

[ ... ]

> diff --git a/drivers/video/backlight/lm3533_bl.c b/drivers/video/backlight/lm3533_bl.c
> index babfd3ceec866..42da652df58d9 100644
> --- a/drivers/video/backlight/lm3533_bl.c
> +++ b/drivers/video/backlight/lm3533_bl.c

[ ... ]

> @@ -295,13 +293,20 @@ static int lm3533_bl_probe(struct platform_device *pdev)
>  	bl->cb.id = lm3533_bl_get_ctrlbank_id(bl);
>  	bl->cb.dev = NULL;			/* until registered */
>  
> +	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s-%d",
> +			      pdev->name, pdev->id);
> +	if (!name)
> +		return -ENOMEM;
> +
>  	memset(&props, 0, sizeof(props));
>  	props.type = BACKLIGHT_RAW;
>  	props.max_brightness = LM3533_BL_MAX_BRIGHTNESS;
> -	props.brightness = pdata->default_brightness;
> -	bd = devm_backlight_device_register(&pdev->dev, pdata->name,
> -					pdev->dev.parent, bl, &lm3533_bl_ops,
> -					&props);
> +	props.brightness = LM3533_BL_MAX_BRIGHTNESS;
> +	device_property_read_u32(&pdev->dev, "default-brightness",
> +				 &props.brightness);

[Severity: Low]
Will this pass an incompatible pointer type? props.brightness is defined as
an int in struct backlight_properties, but device_property_read_u32() expects
a u32 pointer. This could cause compiler warnings or errors.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260528135123.103745-1-clamor95@gmail.com?part=2

^ permalink raw reply	[flat|nested] 16+ messages in thread

* Re: [PATCH v2 2/6] mfd: lm3533: Convert to use OF bindings
  2026-05-28 13:51 ` [PATCH v2 2/6] mfd: lm3533: Convert to use OF bindings Svyatoslav Ryhel
  2026-05-28 14:37   ` sashiko-bot
@ 2026-05-28 14:50   ` Jonathan Cameron
  2026-05-28 15:03     ` Svyatoslav Ryhel
  1 sibling, 1 reply; 16+ messages in thread
From: Jonathan Cameron @ 2026-05-28 14:50 UTC (permalink / raw)
  To: Svyatoslav Ryhel
  Cc: Lee Jones, Daniel Thompson, Jingoo Han, Pavel Machek, Rob Herring,
	Krzysztof Kozlowski, Conor Dooley, David Lechner, Nuno Sá,
	Andy Shevchenko, Helge Deller, Johan Hovold, dri-devel,
	linux-leds, devicetree, linux-kernel, linux-iio, linux-fbdev

On Thu, 28 May 2026 16:51:19 +0300
Svyatoslav Ryhel <clamor95@gmail.com> wrote:

> Since there are no users of this driver via platform data, remove the
> platform data support and switch to using Device Tree bindings.
> Additionally, optimize functions used only by platform data.


At least the IIO ones would have made much the same amount of sense for
dt, just that they weren't having in the first place. I'd prefer that
as a precursor patch to make the rest much more readable.

> 
> Signed-off-by: Svyatoslav Ryhel <clamor95@gmail.com>

I only looked in detail at the iio bit. A few changes requested.

> ---
>  drivers/iio/light/lm3533-als.c      |  95 ++++------
>  drivers/leds/leds-lm3533.c          |  51 ++++--
>  drivers/mfd/lm3533-core.c           | 268 ++++++++++------------------
>  drivers/video/backlight/lm3533_bl.c |  52 ++++--
>  include/linux/mfd/lm3533.h          |  51 +-----
>  5 files changed, 212 insertions(+), 305 deletions(-)
> 
> diff --git a/drivers/iio/light/lm3533-als.c b/drivers/iio/light/lm3533-als.c
> index 99f0b903018c..cbd337b73bd9 100644
> --- a/drivers/iio/light/lm3533-als.c
> +++ b/drivers/iio/light/lm3533-als.c

> @@ -714,59 +720,33 @@ static const struct attribute_group lm3533_als_attribute_group = {
>  	.attrs = lm3533_als_attributes
>  };
>  
> -static int lm3533_als_set_input_mode(struct lm3533_als *als, bool pwm_mode)
> +static int lm3533_als_setup(struct lm3533_als *als)
>  {
> -	u8 mask = LM3533_ALS_INPUT_MODE_MASK;
> -	u8 val;
> +	struct device *dev = &als->pdev.dev;
>  	int ret;
>  
> -	if (pwm_mode)
> -		val = mask;	/* pwm input */
> -	else
> -		val = 0;	/* analog input */
> -
> -	ret = lm3533_update(als->lm3533, LM3533_REG_ALS_CONF, val, mask);
> -	if (ret) {
> -		dev_err(&als->pdev->dev, "failed to set input mode %d\n",
> -								pwm_mode);
> -		return ret;
> -	}
> -
> -	return 0;
> -}
> -
> -static int lm3533_als_set_resistor(struct lm3533_als *als, u8 val)
> -{
> -	int ret;
> -
> -	if (val < LM3533_ALS_RESISTOR_MIN || val > LM3533_ALS_RESISTOR_MAX) {
> -		dev_err(&als->pdev->dev, "invalid resistor value\n");
> -		return -EINVAL;
> -	}
> -
> -	ret = lm3533_write(als->lm3533, LM3533_REG_ALS_RESISTOR_SELECT, val);
> -	if (ret) {
> -		dev_err(&als->pdev->dev, "failed to set resistor\n");
> -		return ret;
> -	}
> +	device_property_read_u32(dev, "ti,resistor-value-ohm",
> +				 &als->r_select);
Does this have a default?  If so the pattern we've recently be setting on for IIO
is
	if (device_property_present(dev, "ti,resistor-value-ohm"))
		ret = device_property_read_u32();
		if (ret) //corrupt property in some fashion
			return ret;
	} else {
		//set default
	}
If there is no default then check it unconditionally.

>  
> -	return 0;
> -}
> +	als->r_select = clamp(als->r_select, LM3533_ALS_RESISTOR_MIN,
> +			      LM3533_ALS_RESISTOR_MAX);
> +	als->r_select = DIV_ROUND_UP(2 * MICRO, 10 * als->r_select);
>  
> -static int lm3533_als_setup(struct lm3533_als *als,
> -			    const struct lm3533_als_platform_data *pdata)
> -{
> -	int ret;
> +	als->pwm_mode = device_property_read_bool(dev, "ti,pwm-mode");
>  
> -	ret = lm3533_als_set_input_mode(als, pdata->pwm_mode);
> +	ret = lm3533_update(lm3533, LM3533_REG_ALS_CONF, als->pwm_mode ?
> +			    LM3533_ALS_INPUT_MODE_MASK : 0,

That's ugly.  Better as

	ret = lm3533_update(lm3533, LM3533_REG_ALS_CONF,
			    als->pwm_mode ? LM3533_ALS_INPUT_MODE_MASK : 0,

Though if there wasn't a layer hiding the regmap, it could just have been

	ret = regmap_assign_bits(lm3533->regmap, LM3533_REG_ALS_CONF,
				 LM3533_ALS_INPUT_MODE_MASK, als->pwm_mode);;

which would have been nicer.

I'm not particularly keen on the swashing of the helpers being in a patch
that is about switching the binding type as feels largely unrelated.
Should really have been a precursor, easier to review patch.


> +			    LM3533_ALS_INPUT_MODE_MASK);
>  	if (ret)
> -		return ret;
> +		return dev_err_probe(dev, ret, "failed to set input mode %d\n",
> +				     als->pwm_mode);
>  
>  	/* ALS input is always high impedance in PWM-mode. */
> -	if (!pdata->pwm_mode) {
> -		ret = lm3533_als_set_resistor(als, pdata->r_select);
> +	if (!als->pwm_mode) {
> +		ret = lm3533_write(lm3533, LM3533_REG_ALS_RESISTOR_SELECT,
> +				   (u8)als->r_select);

Same applies here. Mostly an unrelated change as the only thing switching that
is related to the patch is one parameter.

>  		if (ret)
> -			return ret;
> +			return dev_err_probe(dev, ret, "failed to set resistor\n");
>  	}
>  
>  	return 0;

> @@ -852,25 +825,28 @@ static int lm3533_als_probe(struct platform_device *pdev)
>  	indio_dev->channels = lm3533_als_channels;
>  	indio_dev->num_channels = ARRAY_SIZE(lm3533_als_channels);
>  	indio_dev->name = dev_name(&pdev->dev);
> -	iio_device_set_parent(indio_dev, pdev->dev.parent);

I'm not sure why this was there in the first place.  Hence not sure if it
is safe to remove.


> diff --git a/drivers/leds/leds-lm3533.c b/drivers/leds/leds-lm3533.c
> index 45795f2a1042..d707d43d5526 100644
> --- a/drivers/leds/leds-lm3533.c
> +++ b/drivers/leds/leds-lm3533.c

>  
>  	led->cb.dev = led->cdev.dev;
>  
> -	ret = lm3533_led_setup(led, pdata);
> +	device_property_read_u32(&pdev->dev, "led-max-microamp",
> +				 &led->max_current);

I'd prefer explicit setting of the default to be visible before this, or
the property_present pattern I mention in the IIO review above.

> +	led->max_current = clamp(led->max_current, LM3533_LED_MAX_CURRENT_MIN,
> +				 LM3533_LED_MAX_CURRENT_MAX);

I didn't look any further (busy day!)

^ permalink raw reply	[flat|nested] 16+ messages in thread

* Re: [PATCH v2 1/6] dt-bindings: leds: Document TI LM3533 LED controller
  2026-05-28 13:51 ` [PATCH v2 1/6] dt-bindings: leds: Document TI LM3533 LED controller Svyatoslav Ryhel
  2026-05-28 14:08   ` sashiko-bot
@ 2026-05-28 14:54   ` Jonathan Cameron
  1 sibling, 0 replies; 16+ messages in thread
From: Jonathan Cameron @ 2026-05-28 14:54 UTC (permalink / raw)
  To: Svyatoslav Ryhel
  Cc: Lee Jones, Daniel Thompson, Jingoo Han, Pavel Machek, Rob Herring,
	Krzysztof Kozlowski, Conor Dooley, David Lechner, Nuno Sá,
	Andy Shevchenko, Helge Deller, Johan Hovold, dri-devel,
	linux-leds, devicetree, linux-kernel, linux-iio, linux-fbdev

On Thu, 28 May 2026 16:51:18 +0300
Svyatoslav Ryhel <clamor95@gmail.com> wrote:

> Document the LM3533 - a complete power source for backlight, keypad and
> indicator LEDs in smartphone handsets. The high-voltage inductive boost
> converter provides the power for two series LED strings display backlight
> and keypad functions.
> 
> Signed-off-by: Svyatoslav Ryhel <clamor95@gmail.com>
> ---


The light sensor binding looks fine to me. I didn't check the rest.

Reviewed-by: Jonathan Cameron <jic23@kernel.org> #for light sensor


^ permalink raw reply	[flat|nested] 16+ messages in thread

* Re: [PATCH v2 3/6] mfd: lm3533: Add support for VIN power supply
  2026-05-28 13:51 ` [PATCH v2 3/6] mfd: lm3533: Add support for VIN power supply Svyatoslav Ryhel
@ 2026-05-28 14:56   ` sashiko-bot
  0 siblings, 0 replies; 16+ messages in thread
From: sashiko-bot @ 2026-05-28 14:56 UTC (permalink / raw)
  To: Svyatoslav Ryhel; +Cc: conor+dt, devicetree, robh

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] The `lm3533_cells` array is allocated on the stack without initialization, leading to memory corruption and kernel panics.
--

commit d39c7ac544b69e1a515d2b34cf44f319c6f00c0a
Author: Svyatoslav Ryhel <clamor95@gmail.com>

mfd: lm3533: Add support for VIN power supply

This commit adds support for a 2.7V-5.5V vin power supply to the
lm3533 core driver. It acquires the regulator in the probe function
and toggles it during the enable and disable sequences.

> diff --git a/drivers/mfd/lm3533-core.c b/drivers/mfd/lm3533-core.c
> index 8495e91198711..519f8c16a3f35 100644
> --- a/drivers/mfd/lm3533-core.c
> +++ b/drivers/mfd/lm3533-core.c
[ ... ]
> @@ -324,7 +336,9 @@ static int lm3533_device_init(struct lm3533 *lm3533)
>  	u32 count = 0, reg;
>  	int ret;
>  
> -	lm3533_enable(lm3533);
> +	ret = lm3533_enable(lm3533);
> +	if (ret)
> +		return ret;
>  
>  	device_for_each_child_node_scoped(lm3533->dev, child) {
>  		if (!fwnode_device_is_available(child))

[Severity: High]
This isn't a bug introduced by this patch, but it was introduced earlier in
this patch series (in "mfd: lm3533: Convert to use OF bindings") and
remains unfixed.

Does this code pass uninitialized stack memory to the mfd core?

In lm3533_device_init(), the array is declared on the stack without zero
initialization:

	struct mfd_cell lm3533_cells[LM3533_CELLS_MAX];

When processing the child nodes, only specific fields like name, id, and
of_compatible are assigned. All other fields in the mfd_cell structs,
such as pdata_size, resources, and num_resources, remain populated with
uninitialized stack garbage.

When this array is passed to mfd_add_devices(), the mfd core processes
these garbage values. If pdata_size contains a non-zero garbage value,
mfd_add_device() will call kmemdup() on the garbage platform_data
pointer, which could result in an immediate kernel panic.

Furthermore, if an available child node does not match any of the
supported compatible strings, count is still incremented:

	device_for_each_child_node_scoped(lm3533->dev, child) {
		...
		if (fwnode_device_is_compatible(child, "ti,lm3533-als")) {
			...
		}
		...
		count++;
	}

Could this cause a completely uninitialized cell (with a garbage name
pointer) to be processed? This could also lead to a crash during mfd
registration.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260528135123.103745-1-clamor95@gmail.com?part=3

^ permalink raw reply	[flat|nested] 16+ messages in thread

* Re: [PATCH v2 2/6] mfd: lm3533: Convert to use OF bindings
  2026-05-28 14:50   ` Jonathan Cameron
@ 2026-05-28 15:03     ` Svyatoslav Ryhel
  0 siblings, 0 replies; 16+ messages in thread
From: Svyatoslav Ryhel @ 2026-05-28 15:03 UTC (permalink / raw)
  To: Jonathan Cameron
  Cc: Lee Jones, Daniel Thompson, Jingoo Han, Pavel Machek, Rob Herring,
	Krzysztof Kozlowski, Conor Dooley, David Lechner, Nuno Sá,
	Andy Shevchenko, Helge Deller, Johan Hovold, dri-devel,
	linux-leds, devicetree, linux-kernel, linux-iio, linux-fbdev

чт, 28 трав. 2026 р. о 17:50 Jonathan Cameron <jic23@kernel.org> пише:
>
> On Thu, 28 May 2026 16:51:19 +0300
> Svyatoslav Ryhel <clamor95@gmail.com> wrote:
>
> > Since there are no users of this driver via platform data, remove the
> > platform data support and switch to using Device Tree bindings.
> > Additionally, optimize functions used only by platform data.
>
>
> At least the IIO ones would have made much the same amount of sense for
> dt, just that they weren't having in the first place. I'd prefer that
> as a precursor patch to make the rest much more readable.
>

I can add you preferences into this commit, I don't mind.

> >
> > Signed-off-by: Svyatoslav Ryhel <clamor95@gmail.com>
>
> I only looked in detail at the iio bit. A few changes requested.
>
> > ---
> >  drivers/iio/light/lm3533-als.c      |  95 ++++------
> >  drivers/leds/leds-lm3533.c          |  51 ++++--
> >  drivers/mfd/lm3533-core.c           | 268 ++++++++++------------------
> >  drivers/video/backlight/lm3533_bl.c |  52 ++++--
> >  include/linux/mfd/lm3533.h          |  51 +-----
> >  5 files changed, 212 insertions(+), 305 deletions(-)
> >
> > diff --git a/drivers/iio/light/lm3533-als.c b/drivers/iio/light/lm3533-als.c
> > index 99f0b903018c..cbd337b73bd9 100644
> > --- a/drivers/iio/light/lm3533-als.c
> > +++ b/drivers/iio/light/lm3533-als.c
>
> > @@ -714,59 +720,33 @@ static const struct attribute_group lm3533_als_attribute_group = {
> >       .attrs = lm3533_als_attributes
> >  };
> >
> > -static int lm3533_als_set_input_mode(struct lm3533_als *als, bool pwm_mode)
> > +static int lm3533_als_setup(struct lm3533_als *als)
> >  {
> > -     u8 mask = LM3533_ALS_INPUT_MODE_MASK;
> > -     u8 val;
> > +     struct device *dev = &als->pdev.dev;
> >       int ret;
> >
> > -     if (pwm_mode)
> > -             val = mask;     /* pwm input */
> > -     else
> > -             val = 0;        /* analog input */
> > -
> > -     ret = lm3533_update(als->lm3533, LM3533_REG_ALS_CONF, val, mask);
> > -     if (ret) {
> > -             dev_err(&als->pdev->dev, "failed to set input mode %d\n",
> > -                                                             pwm_mode);
> > -             return ret;
> > -     }
> > -
> > -     return 0;
> > -}
> > -
> > -static int lm3533_als_set_resistor(struct lm3533_als *als, u8 val)
> > -{
> > -     int ret;
> > -
> > -     if (val < LM3533_ALS_RESISTOR_MIN || val > LM3533_ALS_RESISTOR_MAX) {
> > -             dev_err(&als->pdev->dev, "invalid resistor value\n");
> > -             return -EINVAL;
> > -     }
> > -
> > -     ret = lm3533_write(als->lm3533, LM3533_REG_ALS_RESISTOR_SELECT, val);
> > -     if (ret) {
> > -             dev_err(&als->pdev->dev, "failed to set resistor\n");
> > -             return ret;
> > -     }
> > +     device_property_read_u32(dev, "ti,resistor-value-ohm",
> > +                              &als->r_select);
> Does this have a default?  If so the pattern we've recently be setting on for IIO
> is
>         if (device_property_present(dev, "ti,resistor-value-ohm"))
>                 ret = device_property_read_u32();
>                 if (ret) //corrupt property in some fashion
>                         return ret;
>         } else {
>                 //set default
>         }
> If there is no default then check it unconditionally.

default value is LM3533_ALS_RESISTOR_MIN and if no property is present
clamp will ensure that als->r_select will be set to
LM3533_ALS_RESISTOR_MIN

>
> >
> > -     return 0;
> > -}
> > +     als->r_select = clamp(als->r_select, LM3533_ALS_RESISTOR_MIN,
> > +                           LM3533_ALS_RESISTOR_MAX);
> > +     als->r_select = DIV_ROUND_UP(2 * MICRO, 10 * als->r_select);
> >
> > -static int lm3533_als_setup(struct lm3533_als *als,
> > -                         const struct lm3533_als_platform_data *pdata)
> > -{
> > -     int ret;
> > +     als->pwm_mode = device_property_read_bool(dev, "ti,pwm-mode");
> >
> > -     ret = lm3533_als_set_input_mode(als, pdata->pwm_mode);
> > +     ret = lm3533_update(lm3533, LM3533_REG_ALS_CONF, als->pwm_mode ?
> > +                         LM3533_ALS_INPUT_MODE_MASK : 0,
>
> That's ugly.  Better as
>
>         ret = lm3533_update(lm3533, LM3533_REG_ALS_CONF,
>                             als->pwm_mode ? LM3533_ALS_INPUT_MODE_MASK : 0,
>

Yes sure, just followed 80 char limit.

> Though if there wasn't a layer hiding the regmap, it could just have been
>
>         ret = regmap_assign_bits(lm3533->regmap, LM3533_REG_ALS_CONF,
>                                  LM3533_ALS_INPUT_MODE_MASK, als->pwm_mode);;
>
> which would have been nicer.
>
> I'm not particularly keen on the swashing of the helpers being in a patch
> that is about switching the binding type as feels largely unrelated.
> Should really have been a precursor, easier to review patch.
>

Removing of lm3533_update layer is not the scope of this patchset.

>
> > +                         LM3533_ALS_INPUT_MODE_MASK);
> >       if (ret)
> > -             return ret;
> > +             return dev_err_probe(dev, ret, "failed to set input mode %d\n",
> > +                                  als->pwm_mode);
> >
> >       /* ALS input is always high impedance in PWM-mode. */
> > -     if (!pdata->pwm_mode) {
> > -             ret = lm3533_als_set_resistor(als, pdata->r_select);
> > +     if (!als->pwm_mode) {
> > +             ret = lm3533_write(lm3533, LM3533_REG_ALS_RESISTOR_SELECT,
> > +                                (u8)als->r_select);
>
> Same applies here. Mostly an unrelated change as the only thing switching that
> is related to the patch is one parameter.
>

Removing of lm3533_write layer is not the scope of this patchset.

> >               if (ret)
> > -                     return ret;
> > +                     return dev_err_probe(dev, ret, "failed to set resistor\n");
> >       }
> >
> >       return 0;
>
> > @@ -852,25 +825,28 @@ static int lm3533_als_probe(struct platform_device *pdev)
> >       indio_dev->channels = lm3533_als_channels;
> >       indio_dev->num_channels = ARRAY_SIZE(lm3533_als_channels);
> >       indio_dev->name = dev_name(&pdev->dev);
> > -     iio_device_set_parent(indio_dev, pdev->dev.parent);
>
> I'm not sure why this was there in the first place.  Hence not sure if it
> is safe to remove.
>

This is directly related to OF conversion. The iio_device_set_parent
bound indio_dev to parent, and it causes problems with OF now since
als output has its own node and binding it to parent if wrong. Same
story for backlight and leds btw.

>
> > diff --git a/drivers/leds/leds-lm3533.c b/drivers/leds/leds-lm3533.c
> > index 45795f2a1042..d707d43d5526 100644
> > --- a/drivers/leds/leds-lm3533.c
> > +++ b/drivers/leds/leds-lm3533.c
>
> >
> >       led->cb.dev = led->cdev.dev;
> >
> > -     ret = lm3533_led_setup(led, pdata);
> > +     device_property_read_u32(&pdev->dev, "led-max-microamp",
> > +                              &led->max_current);
>
> I'd prefer explicit setting of the default to be visible before this, or
> the property_present pattern I mention in the IIO review above.
>

clamp will ensure that led->max_current will be set to
LM3533_LED_MAX_CURRENT_MIN regardless if it it present

> > +     led->max_current = clamp(led->max_current, LM3533_LED_MAX_CURRENT_MIN,
> > +                              LM3533_LED_MAX_CURRENT_MAX);
>
> I didn't look any further (busy day!)

^ permalink raw reply	[flat|nested] 16+ messages in thread

* Re: [PATCH v2 4/6] mfd: lm3533: Set DMA mask
  2026-05-28 13:51 ` [PATCH v2 4/6] mfd: lm3533: Set DMA mask Svyatoslav Ryhel
@ 2026-05-28 15:28   ` sashiko-bot
  0 siblings, 0 replies; 16+ messages in thread
From: sashiko-bot @ 2026-05-28 15:28 UTC (permalink / raw)
  To: Svyatoslav Ryhel; +Cc: devicetree, robh, conor+dt

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] The `lm3533_cells` array is allocated on the stack without being zero-initialized, and an unconditional `count++` leads to uninitialized elements being passed to the MFD core, risking memory corruption or kernel panics.
- [Medium] An off-by-one error in the validation of the backlight `reg` property allows it to overlap with the LED `reg` address space.
--

commit e3db8e2c46ac0e3ca30554a0b5ae2956e28c6227
Author: Svyatoslav Ryhel <clamor95@gmail.com>

mfd: lm3533: Set DMA mask

Missing coherent_dma_mask assigning triggers a warning in dmesg. This sets
coherent_dma_mask to zero because both the core and cells do not utilize
dma.

> diff --git a/drivers/mfd/lm3533-core.c b/drivers/mfd/lm3533-core.c
> index 519f8c16a3f35..3cfdebf5fb52b 100644
> --- a/drivers/mfd/lm3533-core.c
> +++ b/drivers/mfd/lm3533-core.c
> @@ -526,6 +526,10 @@ static int lm3533_i2c_probe(struct i2c_client *i2c)
>  				   LM3533_BOOST_FREQ_MAX);
>  	lm3533->boost_freq = lm3533->boost_freq / (500 * KILO) - 1;
>  
> +	/* LM3533 and child devices do not use DMA */
> +	i2c->dev.coherent_dma_mask = 0;
> +	i2c->dev.dma_mask = &i2c->dev.coherent_dma_mask;
> +
>  	return lm3533_device_init(lm3533);

[Severity: High]
Does this call to lm3533_device_init() pass uninitialized elements to the mfd
core?  Looking at lm3533_device_init(), the lm3533_cells array is allocated
on the stack without zero-initialization.

If a child node is present in the device tree that does not match any of the
recognized compatible strings, the iteration loop skips the initialization
blocks but still unconditionally executes count++, leaving the array element
with stack garbage:

drivers/mfd/lm3533-core.c:lm3533_device_init() {
    struct mfd_cell lm3533_cells[LM3533_CELLS_MAX];
    u32 count = 0, reg;
    ...
    device_for_each_child_node_scoped(lm3533->dev, child) {
        if (!fwnode_device_is_available(child))
            continue;

        if (count >= LM3533_CELLS_MAX)
            break;

        if (fwnode_device_is_compatible(child, "ti,lm3533-als")) {
            ...
        }
        if (fwnode_device_is_compatible(child, "ti,lm3533-backlight")) {
            ...
        }
        if (fwnode_device_is_compatible(child, "ti,lm3533-leds")) {
            ...
        }

        count++;
    }
    ...
    ret = mfd_add_devices(dev, 0, lm3533_cells, count, NULL, 0, NULL);
}

When this array is passed to mfd_add_devices(), the mfd core will attempt to
dereference a garbage pointer for the device name.  Can this cause memory
corruption or a kernel panic?


[Severity: Medium]
Can an invalid backlight reg value overlap with the LED reg address space?
Looking at lm3533_device_init(), the validation allows reg = 2 to be accepted
for a backlight:

drivers/mfd/lm3533-core.c:lm3533_device_init() {
        ...
        if (fwnode_device_is_compatible(child, "ti,lm3533-backlight")) {
            ret = fwnode_property_read_u32(child, "reg", &reg);
            if (ret || reg > LM3533_HVLED_ID_MAX) {
                dev_err(dev, "invalid backlight reg %d\n", reg);
                continue;
            }
        ...
}

LM3533_HVLED_ID_MAX is 2.  This incorrectly allows reg = 2 to be accepted for
a backlight, assigning it an ID of 2, even though the backlight driver only
supports 2 control banks (IDs 0 and 1).

While the backlight child driver safely returns -EINVAL during probe when it
encounters ID 2, should this check be reg >= LM3533_HVLED_ID_MAX to reject
invalid device tree configurations early in the core driver?

>  }

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260528135123.103745-1-clamor95@gmail.com?part=4

^ permalink raw reply	[flat|nested] 16+ messages in thread

* Re: [PATCH v2 5/6] video: backlight: lm3533_bl: Set initial mapping mode from DT
  2026-05-28 13:51 ` [PATCH v2 5/6] video: backlight: lm3533_bl: Set initial mapping mode from DT Svyatoslav Ryhel
@ 2026-05-28 16:00   ` sashiko-bot
  0 siblings, 0 replies; 16+ messages in thread
From: sashiko-bot @ 2026-05-28 16:00 UTC (permalink / raw)
  To: Svyatoslav Ryhel; +Cc: devicetree, robh, conor+dt

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] The backlight device is exposed to userspace before its hardware initialization is complete.
--

commit 106cefce156b039f4639eecee3b1a98c82987da6
Author: Svyatoslav Ryhel <clamor95@gmail.com>

video: backlight: lm3533_bl: Set initial mapping mode from DT

This commit adds support to obtain the initial mapping mode from DT instead
of leaving it unconfigured. It also updates the linear sysfs code.

> diff --git a/drivers/video/backlight/lm3533_bl.c b/drivers/video/backlight/lm3533_bl.c
> index 42da652df58d9..c03d0d1667e42 100644
> --- a/drivers/video/backlight/lm3533_bl.c
> +++ b/drivers/video/backlight/lm3533_bl.c

[ ... ]

> @@ -317,14 +318,6 @@ static int lm3533_bl_probe(struct platform_device *pdev)
>  
>  	platform_set_drvdata(pdev, bl);
>  
> -	ret = sysfs_create_group(&bd->dev.kobj, &lm3533_bl_attribute_group);
> -	if (ret < 0) {
> -		dev_err(&pdev->dev, "failed to create sysfs attributes\n");
> -		return ret;
> -	}
> -
> -	backlight_update_status(bd);
> -
>  	device_property_read_u32(&pdev->dev, "led-max-microamp",
>  				 &bl->max_current);
>  	bl->max_current = clamp(bl->max_current, LM3533_LED_MAX_CURRENT_MIN,
> @@ -333,9 +326,20 @@ static int lm3533_bl_probe(struct platform_device *pdev)
>  	bl->pwm = 0;
>  	device_property_read_u32(&pdev->dev, "ti,pwm-config-mask", &bl->pwm);
>  
> +	bl->linear = device_property_read_bool(&pdev->dev,
> +					       "ti,linear-mapping-mode");
> +
>  	ret = lm3533_bl_setup(bl);

[Severity: High]
This is a pre-existing issue, but I noticed a potential race condition here
with devm_backlight_device_register() being called earlier in this function.

When devm_backlight_device_register() is called, it creates the device in
sysfs, exposes standard attributes like brightness, and immediately fires a
KOBJ_ADD uevent.

Could a userspace daemon like systemd-backlight react to this uevent and
write a saved brightness value concurrently with the rest of this probe
function?

If that happens, it would trigger lm3533_bl_ops.update_status, which calls
lm3533_ctrlbank_set_brightness() to configure the hardware to drive the LEDs.

Because the driver has not yet read device tree limits like led-max-microamp
and applied them via lm3533_bl_setup() and lm3533_ctrlbank_set_max_current(),
could driving the LEDs before configuring the hardware's maximum safe current
limit result in physical hardware damage?

>  	if (ret)
> -		goto err_sysfs_remove;
> +		return ret;
> +
> +	ret = sysfs_create_group(&bd->dev.kobj, &lm3533_bl_attribute_group);
> +	if (ret < 0) {
> +		dev_err(&pdev->dev, "failed to create sysfs attributes\n");
> +		return ret;
> +	}
> +
> +	backlight_update_status(bd);

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260528135123.103745-1-clamor95@gmail.com?part=5

^ permalink raw reply	[flat|nested] 16+ messages in thread

* Re: [PATCH v2 6/6] video: leds: backlight: lm3533: Support getting LED sources from DT
  2026-05-28 13:51 ` [PATCH v2 6/6] video: leds: backlight: lm3533: Support getting LED sources " Svyatoslav Ryhel
@ 2026-05-28 16:33   ` sashiko-bot
  0 siblings, 0 replies; 16+ messages in thread
From: sashiko-bot @ 2026-05-28 16:33 UTC (permalink / raw)
  To: Svyatoslav Ryhel; +Cc: robh, conor+dt, devicetree

Thank you for your contribution! Sashiko AI review found 5 potential issue(s) to consider:
- [High] Hardcoded register masks clobber sibling device configurations.
- [Medium] Missing bounds validation on device tree shift values causes undefined behavior.
- [Medium] Premature sysfs group removal in error path triggers kernel warnings.
- [Low] Incorrect boundary check allows an out-of-bounds LVLED index.
- [Low] Improper handling of negative error codes from device property count via unsigned wrapping.
--

commit e5414513aab84157f65b5403f08affee4717c3cb
Author: Svyatoslav Ryhel <clamor95@gmail.com>

video: leds: backlight: lm3533: Support getting LED sources from DT
    
Add Control Bank to HVLED/LVLED muxing support based on the led-sources
defined in the device tree.

> diff --git a/drivers/leds/leds-lm3533.c b/drivers/leds/leds-lm3533.c
> index d707d43d55260..07390bba9a48c 100644
> --- a/drivers/leds/leds-lm3533.c
> +++ b/drivers/leds/leds-lm3533.c
[ ... ]
> @@ -639,7 +649,33 @@ static const struct attribute_group *lm3533_led_attribute_groups[] = {
>  
>  static int lm3533_led_setup(struct lm3533_led *led)
>  {
> -	int ret;
> +	u32 output_cfg_shift = 0;
> +	u32 output_cfg_val = 0;
> +	int ret, i;
> +
> +	if (led->num_leds) {
> +		for (i = 0; i < led->num_leds; i++) {
> +			if (led->leds[i] > LM3533_LVCTRLBANK_MAX)

[Severity: Low]
Is this boundary check correct? LM3533_LVCTRLBANK_MAX appears to be 5, so
using greater-than allows an index of 5 to pass.

Since there are only 5 LV LEDs mapped to indices 0 through 4, would an index
of 5 result in calculating a bit shift for a non-existent LVLED6?

> +				continue;
> +
> +			output_cfg_shift = led->leds[i] * 2;
> +			output_cfg_val |= led->id << output_cfg_shift;
> +		}
> +
> +		/* LVLED1, LVLED2 and LVLED3 */
> +		ret = lm3533_update(led->lm3533, LM3533_REG_OUTPUT_CONF1,
> +				    output_cfg_val << OUTPUT_CONF1_SHIFT,
> +				    OUTPUT_CONF1_MASK);

[Severity: High]
If a mask like OUTPUT_CONF1_MASK is used for lm3533_update() and it covers all
LEDs, will it unconditionally clear the configuration bits for any LEDs not
assigned to the current bank?

For example, if Bank 0 configures one LED and then Bank 1 configures another,
does the second update overwrite and clear the first one's configuration since
the mask is static? Should the register mask be dynamically generated based on
the LEDs actually being configured?

> +		if (ret)
> +			return ret;
> +
> +		/* LVLED4 and LVLED5 */
> +		ret = lm3533_update(led->lm3533, LM3533_REG_OUTPUT_CONF2,
> +				    output_cfg_val >> OUTPUT_CONF2_SHIFT,
> +				    OUTPUT_CONF2_MASK);
> +		if (ret)
> +			return ret;
> +	}
[ ... ]
> diff --git a/drivers/video/backlight/lm3533_bl.c b/drivers/video/backlight/lm3533_bl.c
> index c03d0d1667e42..82b46a531dd27 100644
> --- a/drivers/video/backlight/lm3533_bl.c
> +++ b/drivers/video/backlight/lm3533_bl.c
[ ... ]
> @@ -248,7 +254,8 @@ static struct attribute_group lm3533_bl_attribute_group = {
>  static int lm3533_bl_setup(struct lm3533_bl *bl)
>  {
>  	int id = lm3533_bl_get_ctrlbank_id(bl);
> -	int ret;
> +	u32 output_cfg_val = 0;
> +	int ret, i;
>  
>  	ret = lm3533_update(bl->lm3533, LM3533_REG_CTRLBANK_AB_BCONF,
>  			    bl->linear ? CTRLBANK_AB_BCONF_MODE(id) : 0,
> @@ -256,6 +263,16 @@ static int lm3533_bl_setup(struct lm3533_bl *bl)
>  	if (ret)
>  		return ret;
>  
> +	if (bl->num_leds) {
> +		for (i = 0; i < bl->num_leds; i++)
> +			output_cfg_val |= id << bl->led_strings[i];

[Severity: Medium]
Since the values from bl->led_strings arrays are read directly from the device
tree property without bounds checking, could a malformed device tree provide a
value of 32 or greater and cause an out-of-bounds bitwise shift here?

> +
> +		ret = lm3533_update(bl->lm3533, LM3533_REG_OUTPUT_CONF1,
> +				    output_cfg_val, OUTPUT_CONF1_MASK);
> +		if (ret)
> +			return ret;
> +	}
[ ... ]
> @@ -329,6 +346,24 @@ static int lm3533_bl_probe(struct platform_device *pdev)
>  	bl->linear = device_property_read_bool(&pdev->dev,
>  					       "ti,linear-mapping-mode");
>  
> +	bl->num_leds = device_property_count_u32(&pdev->dev, "led-sources");

[Severity: Low]
Looking at the struct definition, bl->num_leds is declared as a u32.

If device_property_count_u32() returns a negative error code like -EINVAL,
does that get implicitly cast to a very large positive unsigned integer?

The subsequent bounds check would safely fail, but could this be avoided by
using an int for the count, similar to what is done in lm3533_led_probe()?

> +
> +	/*
> +	 * If led-sources property is not set then either this Control Bank uses
> +	 * its default HVLED or is not linked to any HVLED at all.
> +	 */
> +	if (bl->num_leds > 0 && bl->num_leds <= LM3533_HVCTRLBANK_COUNT) {
> +		ret = device_property_read_u32_array(&pdev->dev, "led-sources",
> +						     bl->led_strings,
> +						     bl->num_leds);
> +		if (ret) {
> +			dev_err(&pdev->dev, "failed to get led-sources\n");
> +			goto err_sysfs_remove;

[Severity: Medium]
If device_property_read_u32_array() fails, this jumps to err_sysfs_remove.

Looking at lm3533_bl_probe(), sysfs_create_group() is called later in the
probe sequence.

Does calling sysfs_remove_group() on an uncreated sysfs group here trigger a
kernel warning? Should the error path at this stage simply return the error
code instead?

> +		}
> +	} else {
> +		bl->num_leds = 0;
> +	}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260528135123.103745-1-clamor95@gmail.com?part=6

^ permalink raw reply	[flat|nested] 16+ messages in thread

end of thread, other threads:[~2026-05-28 16:33 UTC | newest]

Thread overview: 16+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-05-28 13:51 [PATCH v2 0/6] mfd: lm3533: convert to OF bindings, improve support Svyatoslav Ryhel
2026-05-28 13:51 ` [PATCH v2 1/6] dt-bindings: leds: Document TI LM3533 LED controller Svyatoslav Ryhel
2026-05-28 14:08   ` sashiko-bot
2026-05-28 14:54   ` Jonathan Cameron
2026-05-28 13:51 ` [PATCH v2 2/6] mfd: lm3533: Convert to use OF bindings Svyatoslav Ryhel
2026-05-28 14:37   ` sashiko-bot
2026-05-28 14:50   ` Jonathan Cameron
2026-05-28 15:03     ` Svyatoslav Ryhel
2026-05-28 13:51 ` [PATCH v2 3/6] mfd: lm3533: Add support for VIN power supply Svyatoslav Ryhel
2026-05-28 14:56   ` sashiko-bot
2026-05-28 13:51 ` [PATCH v2 4/6] mfd: lm3533: Set DMA mask Svyatoslav Ryhel
2026-05-28 15:28   ` sashiko-bot
2026-05-28 13:51 ` [PATCH v2 5/6] video: backlight: lm3533_bl: Set initial mapping mode from DT Svyatoslav Ryhel
2026-05-28 16:00   ` sashiko-bot
2026-05-28 13:51 ` [PATCH v2 6/6] video: leds: backlight: lm3533: Support getting LED sources " Svyatoslav Ryhel
2026-05-28 16:33   ` sashiko-bot

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox