* Re: [PATCH v3 2/4] Input: snvs_pwrkey - replace hardcoding -EINVAL with original error code
From: Frank Li @ 2026-06-15 14:38 UTC (permalink / raw)
To: joy.zou
Cc: Dmitry Torokhov, Frank Li, Bough Chen, Peng Fan, Jacky Bai, Ye Li,
imx, linux-input, linux-kernel, Joy Zou
In-Reply-To: <20260615-b4-pwrkey-v3-2-9510b1173f6e@oss.nxp.com>
On Mon, Jun 15, 2026 at 03:52:15PM +0800, joy.zou@oss.nxp.com wrote:
Nit: subject
Input: snvs_pwrkey: propagate error code of platform_get_irq()
>
> Hardcoding -EINVAL discards the actual error code, which breaks probe
> deferral (-EPROBE_DEFER) and loses critical diagnostic information
> needed for proper kernel error handling.
>
> Signed-off-by: Joy Zou <joy.zou@nxp.com>
> ---
Reviewed-by: Frank Li <Frank.Li@nxp.com>
> drivers/input/keyboard/snvs_pwrkey.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/input/keyboard/snvs_pwrkey.c b/drivers/input/keyboard/snvs_pwrkey.c
> index 748196fcce75..a291812e6d22 100644
> --- a/drivers/input/keyboard/snvs_pwrkey.c
> +++ b/drivers/input/keyboard/snvs_pwrkey.c
> @@ -148,7 +148,7 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
>
> pdata->irq = platform_get_irq(pdev, 0);
> if (pdata->irq < 0)
> - return -EINVAL;
> + return pdata->irq;
>
> error = of_property_read_u32(np, "power-off-time-sec", &val);
> if (!error) {
>
> --
> 2.34.1
>
>
^ permalink raw reply
* Re: [PATCH v3 02/10] Input: cap11xx - remove unused register macros
From: sashiko-bot @ 2026-06-15 14:34 UTC (permalink / raw)
To: Jun Yan; +Cc: conor+dt, dmitry.torokhov, robh, devicetree, linux-input
In-Reply-To: <20260615142103.352163-3-jerrysteve1101@gmail.com>
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
New issues:
- [Medium] Removing sensor delta registers from the volatile register list causes regmap to incorrectly cache their values, breaking debugfs observability.
Pre-existing issues:
- [High] The driver requests its IRQ after registering the input device, creating a race condition where an unhandled interrupt can permanently disable the device.
--
commit 72bbdd7bb3155f054afabfd004f5e097d568001b
Author: Jun Yan <jerrysteve1101@gmail.com>
Input: cap11xx - remove unused register macros
Remove unused register address macros and unused definitions in
the cap11xx_reg_defaults array and cap11xx_volatile_reg. This cleanup
reduces code clutter and makes the driver easier to maintain.
> diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
> index 485d8ba977235..686174722204c 100644
> --- a/drivers/input/keyboard/cap11xx.c
> +++ b/drivers/input/keyboard/cap11xx.c
[ ... ]
> @@ -149,12 +97,6 @@ static bool cap11xx_volatile_reg(struct device *dev, unsigned int reg)
> switch (reg) {
> case CAP11XX_REG_MAIN_CONTROL:
> case CAP11XX_REG_SENSOR_INPUT:
> - case CAP11XX_REG_SENOR_DELTA(0):
> - case CAP11XX_REG_SENOR_DELTA(1):
> - case CAP11XX_REG_SENOR_DELTA(2):
> - case CAP11XX_REG_SENOR_DELTA(3):
> - case CAP11XX_REG_SENOR_DELTA(4):
> - case CAP11XX_REG_SENOR_DELTA(5):
[Severity: Medium]
Does removing the sensor delta registers from the volatile list cause a
regression for observability via the regmap debugfs interface?
These registers contain real-time capacitance delta hardware values that are
continuously updated by the device. Treating them as non-volatile causes
regmap to cache them on the first read, resulting in stale values for any
subsequent reads by tuning tools or developers.
> return true;
> }
>
[Severity: High]
This isn't a bug introduced by this patch, but I noticed a pre-existing probe
ordering flaw in cap11xx_i2c_probe():
error = input_register_device(priv->idev);
if (error)
return error;
error = devm_request_threaded_irq(dev, i2c_client->irq,
NULL, cap11xx_thread_func,
IRQF_ONESHOT, dev_name(dev), priv);
Could this sequence lead to the interrupt being permanently disabled?
Since input_register_device() exposes the device to userspace, a daemon
can immediately open the device, waking the sensor from deep sleep.
If the sensor generates a hardware interrupt before
devm_request_threaded_irq() completes, the generic IRQ core will receive an
interrupt with no registered handler.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260615142103.352163-1-jerrysteve1101@gmail.com?part=2
^ permalink raw reply
* Re: [PATCH v3 06/10] Input: cap11xx - add reset gpio support
From: sashiko-bot @ 2026-06-15 14:29 UTC (permalink / raw)
To: Jun Yan; +Cc: linux-input, robh, dmitry.torokhov, conor+dt, devicetree
In-Reply-To: <20260615142103.352163-7-jerrysteve1101@gmail.com>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] Coding style violations: redundant 'else' after 'return' and inconsistent brace usage.
--
commit 2a7317102372f10d4bd76864cfeaec2d7955c415
Author: Jun Yan <jerrysteve1101@gmail.com>
Input: cap11xx - add reset gpio support
This commit adds support for an optional hardware reset pin on CAP11xx
devices to improve reliability and ensure proper initialization during probe.
> diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
> --- a/drivers/input/keyboard/cap11xx.c
> +++ b/drivers/input/keyboard/cap11xx.c
[ ... ]
> @@ -452,6 +457,16 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
> if (IS_ERR(priv->regmap))
> return PTR_ERR(priv->regmap);
>
> + priv->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
> + if (IS_ERR(priv->reset_gpio))
> + return dev_err_probe(dev, PTR_ERR(priv->reset_gpio),
> + "Failed to get 'reset' GPIO\n");
> + else if (priv->reset_gpio) {
[Severity: Low]
This isn't a bug, but does this follow the standard kernel coding style?
Since the preceding if statement ends with a return, the else keyword here
is redundant. Additionally, kernel style guidelines generally prefer that if
one branch of a conditional requires braces, all branches should use them.
Could this be simplified by dropping the else and just using a separate if
statement for checking priv->reset_gpio?
> + usleep_range(CAP11XX_T_RST_FILT_MIN_US, CAP11XX_T_RST_FILT_MIN_US * 2);
> + gpiod_set_value_cansleep(priv->reset_gpio, 0);
> + msleep(CAP11XX_T_RST_ON_MIN_MS);
> + }
> +
> error = regmap_read(priv->regmap, CAP11XX_REG_PRODUCT_ID, &val);
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260615142103.352163-1-jerrysteve1101@gmail.com?part=6
^ permalink raw reply
* [PATCH v3 10/10] Input: cap11xx - add support for CAP1114
From: Jun Yan @ 2026-06-15 14:20 UTC (permalink / raw)
To: Dmitry Torokhov, Rob Herring, Krzysztof Kozlowski, Conor Dooley
Cc: Jun Yan, linux-input, devicetree, linux-kernel
In-Reply-To: <20260615142103.352163-1-jerrysteve1101@gmail.com>
CAP1114 is a 14-channel capacitive touch sensor with 11 LED outputs
and hardware reset support.
The CAP1114 uses two control registers for LED output management and
requires two button status registers for touch input state reporting.
By default, channels CS8~CS14 operate as a single grouped block.
Set the corresponding register enable bit to enable these channels as
independent touch inputs. Note these channels share the input threshold
of the eighth entry, causing num_sensor_thresholds to differ from
num_channels.
Signed-off-by: Jun Yan <jerrysteve1101@gmail.com>
---
drivers/input/keyboard/cap11xx.c | 73 ++++++++++++++++++++++++++++++--
1 file changed, 69 insertions(+), 4 deletions(-)
diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index c48ee8520a27..187a212dfa8f 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -18,6 +18,12 @@
#include <linux/gpio/consumer.h>
#include <linux/bitfield.h>
+#define CAP1114_REG_BUTTON_STATUS1 0x03
+#define CAP1114_REG_BUTTON_STATUS2 0x04
+#define CAP1114_REG_CONFIG2 0x40
+#define CAP1114_REG_CONFIG2_VOL_UP_DOWN BIT(1)
+#define CAP1114_REG_LED_OUTPUT_CONTROL1 0x73
+
#define CAP11XX_REG_MAIN_CONTROL 0x00
#define CAP11XX_REG_MAIN_CONTROL_GAIN_SHIFT (6)
#define CAP11XX_REG_MAIN_CONTROL_GAIN_MASK (0xc0)
@@ -82,6 +88,7 @@ struct cap11xx_hw_model {
unsigned int num_leds;
unsigned int num_sensor_thresholds;
bool has_gain;
+ bool has_grouped_sensors;
bool has_irq_config;
bool has_repeat_en;
bool has_sensitivity_control;
@@ -98,6 +105,8 @@ static const struct reg_default cap11xx_reg_defaults[] = {
{ CAP11XX_REG_SENSOR_THRESH(3), 0x40 },
{ CAP11XX_REG_SENSOR_THRESH(4), 0x40 },
{ CAP11XX_REG_SENSOR_THRESH(5), 0x40 },
+ { CAP11XX_REG_SENSOR_THRESH(6), 0x40 },
+ { CAP11XX_REG_SENSOR_THRESH(7), 0x40 },
{ CAP11XX_REG_CONFIG2, 0x40 },
};
@@ -106,6 +115,12 @@ static bool cap11xx_volatile_reg(struct device *dev, unsigned int reg)
switch (reg) {
case CAP11XX_REG_MAIN_CONTROL:
case CAP11XX_REG_SENSOR_INPUT:
+ /*
+ * CAP1114_REG_BUTTON_STATUS1 (CAP11XX_REG_SENSOR_INPUT) and
+ * CAP1114_REG_BUTTON_STATUS2 is volatile for the CAP1114,
+ * which supports more than 8 touch channels.
+ */
+ case CAP1114_REG_BUTTON_STATUS2:
return true;
}
@@ -285,6 +300,17 @@ static int cap11xx_init_keys(struct cap11xx_priv *priv)
of_property_read_u32_array(node, "linux,keycodes",
priv->keycodes, priv->model->num_channels);
+ /*
+ * CAP1114 needs dedicated configuration to split
+ * grouped sensors into independent inputs.
+ */
+ if (priv->model->has_grouped_sensors) {
+ error = regmap_set_bits(priv->regmap, CAP1114_REG_CONFIG2,
+ CAP1114_REG_CONFIG2_VOL_UP_DOWN);
+ if (error)
+ return error;
+ }
+
if (priv->model->has_repeat_en) {
/* Disable autorepeat. The Linux input system has its own handling. */
error = regmap_write(priv->regmap, CAP11XX_REG_REPEAT_RATE, 0);
@@ -313,6 +339,21 @@ static irqreturn_t cap11xx_thread_func(int irq_num, void *data)
if (ret < 0)
goto out;
+ if (priv->model->num_channels > 8) {
+ unsigned int status2;
+
+ ret = regmap_read(priv->regmap, priv->model->sensor_input_reg_base + 1, &status2);
+ if (ret < 0)
+ goto out;
+
+ /*
+ * CAP1114 STATUS1 register only contains data for the first 6 channels.
+ * the remaining channels is stored in STATUS2.
+ */
+ status &= GENMASK(5, 0);
+ status |= FIELD_PREP(GENMASK(13, 6), status2);
+ }
+
for (i = 0; i < priv->idev->keycodemax; i++)
input_report_key(priv->idev, priv->keycodes[i],
status & (1 << i));
@@ -362,10 +403,16 @@ static int cap11xx_led_set(struct led_classdev *cdev,
* limitation. Brightness levels per LED are either
* 0 (OFF) and 1 (ON).
*/
- return regmap_update_bits(priv->regmap,
- priv->model->led_output_control_reg_base,
- BIT(led->reg),
- value ? BIT(led->reg) : 0);
+ if (led->reg >= 8)
+ return regmap_update_bits(priv->regmap,
+ priv->model->led_output_control_reg_base + 1,
+ BIT(led->reg - 8),
+ value ? BIT(led->reg - 8) : 0);
+ else
+ return regmap_update_bits(priv->regmap,
+ priv->model->led_output_control_reg_base,
+ BIT(led->reg),
+ value ? BIT(led->reg) : 0);
}
static int cap11xx_init_leds(struct device *dev,
@@ -396,6 +443,14 @@ static int cap11xx_init_leds(struct device *dev,
if (error)
return error;
+ if (num_leds > 8) {
+ error = regmap_update_bits(priv->regmap,
+ priv->model->led_output_control_reg_base + 1,
+ GENMASK(num_leds - 8 - 1, 0), 0);
+ if (error)
+ return error;
+ }
+
duty_val = FIELD_PREP(CAP11XX_REG_LED_DUTY_MAX_MASK,
CAP11XX_REG_LED_DUTY_MAX_VALUE);
@@ -573,6 +628,14 @@ static const struct cap11xx_hw_model cap1106_model = {
.has_repeat_en = true,
};
+static const struct cap11xx_hw_model cap1114_model = {
+ .product_id = 0x3a,
+ .num_channels = 14, .num_leds = 11, .num_sensor_thresholds = 8,
+ .led_output_control_reg_base = CAP1114_REG_LED_OUTPUT_CONTROL1,
+ .sensor_input_reg_base = CAP1114_REG_BUTTON_STATUS1,
+ .has_grouped_sensors = true,
+};
+
static const struct cap11xx_hw_model cap1126_model = {
.product_id = 0x53,
.num_channels = 6, .num_leds = 2, .num_sensor_thresholds = 6,
@@ -629,6 +692,7 @@ static const struct cap11xx_hw_model cap1298_model = {
static const struct of_device_id cap11xx_dt_ids[] = {
{ .compatible = "microchip,cap1106", .data = &cap1106_model },
+ { .compatible = "microchip,cap1114", .data = &cap1114_model },
{ .compatible = "microchip,cap1126", .data = &cap1126_model },
{ .compatible = "microchip,cap1188", .data = &cap1188_model },
{ .compatible = "microchip,cap1203", .data = &cap1203_model },
@@ -641,6 +705,7 @@ MODULE_DEVICE_TABLE(of, cap11xx_dt_ids);
static const struct i2c_device_id cap11xx_i2c_ids[] = {
{ .name = "cap1106", .driver_data = (kernel_ulong_t)&cap1106_model },
+ { .name = "cap1114", .driver_data = (kernel_ulong_t)&cap1114_model },
{ .name = "cap1126", .driver_data = (kernel_ulong_t)&cap1126_model },
{ .name = "cap1188", .driver_data = (kernel_ulong_t)&cap1188_model },
{ .name = "cap1203", .driver_data = (kernel_ulong_t)&cap1203_model },
--
2.54.0
^ permalink raw reply related
* [PATCH v3 09/10] dt-bindings: input: microchip,cap11xx: Add CAP1114 support
From: Jun Yan @ 2026-06-15 14:20 UTC (permalink / raw)
To: Dmitry Torokhov, Rob Herring, Krzysztof Kozlowski, Conor Dooley
Cc: Jun Yan, linux-input, devicetree, linux-kernel
In-Reply-To: <20260615142103.352163-1-jerrysteve1101@gmail.com>
CAP1114 is a 14-channel capacitive touch sensor with 11 LED outputs
and hardware reset support.
Add the compatible string for CAP1114, add its datasheet URL,
update the maximum of LED channel reg, and add constraint for
linux,keycodes.
Previously, the LED reg property had a default maximum of 7 for CAP1188.
With the addition of CAP1114, the default maximum is now 11.
An if-then constraint is added to limit the LED count for CAP1188.
Update description for microchip,input-threshold: CAP1114 only provides
eight threshold entries, which does not match its total channel count.
CAP1114 does not support microchip,signal-guard and
microchip,calib-sensitivity.
Add CAP1114 to the unsupported enum list.
Signed-off-by: Jun Yan <jerrysteve1101@gmail.com>
---
.../bindings/input/microchip,cap11xx.yaml | 37 ++++++++++++++++++-
1 file changed, 35 insertions(+), 2 deletions(-)
diff --git a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
index 778ec6d659a8..153099d59d1a 100644
--- a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
+++ b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
@@ -12,6 +12,7 @@ description: |
For more product information please see the links below:
CAP1106: https://ww1.microchip.com/downloads/en/DeviceDoc/00001624B.pdf
+ CAP1114: https://ww1.microchip.com/downloads/en/DeviceDoc/00002444A.pdf
CAP1126: https://ww1.microchip.com/downloads/en/DeviceDoc/00001623B.pdf
CAP1188: https://ww1.microchip.com/downloads/en/DeviceDoc/00001620C.pdf
CAP1203: https://ww1.microchip.com/downloads/en/DeviceDoc/00001572B.pdf
@@ -26,6 +27,7 @@ properties:
compatible:
enum:
- microchip,cap1106
+ - microchip,cap1114
- microchip,cap1126
- microchip,cap1188
- microchip,cap1203
@@ -62,7 +64,7 @@ properties:
linux,keycodes:
minItems: 3
- maxItems: 8
+ maxItems: 14
description: |
Specifies an array of numeric keycode values to
be used for the channels. If this property is
@@ -122,6 +124,8 @@ properties:
is required for a touch to be registered, making the touch sensor less
sensitive.
The number of entries must correspond to the number of channels.
+ CAP1114 is an exception where channels 8~14 reuse the eighth entry's
+ threshold, so counts differ.
microchip,calib-sensitivity:
$ref: /schemas/types.yaml#/definitions/uint32-array
@@ -149,7 +153,7 @@ patternProperties:
reg:
description: LED channel number
minimum: 0
- maximum: 7
+ maximum: 10
label: true
@@ -178,6 +182,21 @@ allOf:
properties:
reset-gpios: false
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - microchip,cap1114
+ then:
+ properties:
+ linux,keycodes:
+ minItems: 14
+ else:
+ properties:
+ linux,keycodes:
+ maxItems: 8
+
- if:
properties:
compatible:
@@ -205,12 +224,26 @@ allOf:
reg:
maximum: 1
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - microchip,cap1188
+ then:
+ patternProperties:
+ "^led@":
+ properties:
+ reg:
+ maximum: 7
+
- if:
properties:
compatible:
contains:
enum:
- microchip,cap1106
+ - microchip,cap1114
- microchip,cap1126
- microchip,cap1188
- microchip,cap1203
--
2.54.0
^ permalink raw reply related
* [PATCH v3 08/10] Input: cap11xx - guard unsupported DT properties before parsing
From: Jun Yan @ 2026-06-15 14:20 UTC (permalink / raw)
To: Dmitry Torokhov, Rob Herring, Krzysztof Kozlowski, Conor Dooley
Cc: Jun Yan, linux-input, devicetree, linux-kernel
In-Reply-To: <20260615142103.352163-1-jerrysteve1101@gmail.com>
Check of_property_present() before parsing microchip,calib-sensitivity
and microchip,signal-guard, so that models which do not support these
properties (e.g. CAP1114) skip the parsing entirely.
This prevents a potential buffer overflow in calib_sensitivities[8] and
signal_guard_inputs_mask when a model with more than 8 channels
(CAP1114 has 14) would otherwise call of_property_read_u32_array()
with num_channels as the element count.
Signed-off-by: Jun Yan <jerrysteve1101@gmail.com>
---
drivers/input/keyboard/cap11xx.c | 52 +++++++++++++++++---------------
1 file changed, 27 insertions(+), 25 deletions(-)
diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index 2e9382a721e9..c48ee8520a27 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -224,10 +224,13 @@ static int cap11xx_init_keys(struct cap11xx_priv *priv)
}
}
- if (!of_property_read_u32_array(node, "microchip,calib-sensitivity",
- priv->calib_sensitivities,
- priv->model->num_channels)) {
- if (priv->model->has_sensitivity_control) {
+ if (of_property_present(node, "microchip,calib-sensitivity")) {
+ if (!priv->model->has_sensitivity_control) {
+ dev_warn(dev,
+ "This model doesn't support 'calib-sensitivity'\n");
+ } else if (!of_property_read_u32_array(node, "microchip,calib-sensitivity",
+ priv->calib_sensitivities,
+ priv->model->num_channels)) {
for (i = 0; i < priv->model->num_channels; i++) {
if (!is_power_of_2(priv->calib_sensitivities[i]) ||
priv->calib_sensitivities[i] > 4) {
@@ -247,32 +250,31 @@ static int cap11xx_init_keys(struct cap11xx_priv *priv)
if (error)
return error;
}
- } else {
- dev_warn(dev,
- "This model doesn't support 'calib-sensitivity'\n");
}
}
- for (i = 0; i < priv->model->num_channels; i++) {
- if (!of_property_read_u32_index(node, "microchip,signal-guard",
- i, &u32_val)) {
- if (u32_val > 1)
- return -EINVAL;
- if (u32_val)
- priv->signal_guard_inputs_mask |= 0x01 << i;
- }
- }
-
- if (priv->signal_guard_inputs_mask) {
- if (priv->model->has_signal_guard) {
- error = regmap_write(priv->regmap,
- CAP11XX_REG_SIGNAL_GUARD_ENABLE,
- priv->signal_guard_inputs_mask);
- if (error)
- return error;
- } else {
+ if (of_property_present(node, "microchip,signal-guard")) {
+ if (!priv->model->has_signal_guard) {
dev_warn(dev,
"This model doesn't support 'signal-guard'\n");
+ } else {
+ for (i = 0; i < priv->model->num_channels; i++) {
+ if (!of_property_read_u32_index(node, "microchip,signal-guard",
+ i, &u32_val)) {
+ if (u32_val > 1)
+ return -EINVAL;
+ if (u32_val)
+ priv->signal_guard_inputs_mask |= 0x01 << i;
+ }
+ }
+
+ if (priv->signal_guard_inputs_mask) {
+ error = regmap_write(priv->regmap,
+ CAP11XX_REG_SIGNAL_GUARD_ENABLE,
+ priv->signal_guard_inputs_mask);
+ if (error)
+ return error;
+ }
}
}
--
2.54.0
^ permalink raw reply related
* [PATCH v3 07/10] Input: cap11xx - refactor code for better CAP1114 support.
From: Jun Yan @ 2026-06-15 14:20 UTC (permalink / raw)
To: Dmitry Torokhov, Rob Herring, Krzysztof Kozlowski, Conor Dooley
Cc: Jun Yan, linux-input, devicetree, linux-kernel
In-Reply-To: <20260615142103.352163-1-jerrysteve1101@gmail.com>
Extend cap11xx_hw_model structure to support CAP1114 with
different register offsets and hardware characteristics:
- led_output_control_reg_base: different address on CAP1114
- sensor_input_reg_base: different address on CAP1114
- num_sensor_thresholds: separate value from num_channels for CAP1114
- has_repeat_en: repeat enable support, disabled by default on CAP1114
Include linux/bits.h, update the register operations related to LEDs.
Signed-off-by: Jun Yan <jerrysteve1101@gmail.com>
---
drivers/input/keyboard/cap11xx.c | 73 +++++++++++++++++++++++---------
1 file changed, 53 insertions(+), 20 deletions(-)
diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index 3d75c0f90752..2e9382a721e9 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -5,6 +5,7 @@
* (c) 2014 Daniel Mack <linux@zonque.org>
*/
+#include <linux/bits.h>
#include <linux/delay.h>
#include <linux/kernel.h>
#include <linux/module.h>
@@ -35,7 +36,6 @@
#define CAP11XX_REG_LED_DUTY_CYCLE_4 0x93
#define CAP11XX_REG_LED_DUTY_MAX_MASK (0xf0)
-#define CAP11XX_REG_LED_DUTY_MAX_MASK_SHIFT (4)
#define CAP11XX_REG_LED_DUTY_MAX_VALUE (15)
#define CAP11XX_REG_PRODUCT_ID 0xfd
@@ -76,10 +76,14 @@ struct cap11xx_priv {
struct cap11xx_hw_model {
u8 product_id;
+ u8 led_output_control_reg_base;
+ u8 sensor_input_reg_base;
unsigned int num_channels;
unsigned int num_leds;
+ unsigned int num_sensor_thresholds;
bool has_gain;
bool has_irq_config;
+ bool has_repeat_en;
bool has_sensitivity_control;
bool has_signal_guard;
};
@@ -204,8 +208,8 @@ static int cap11xx_init_keys(struct cap11xx_priv *priv)
}
if (!of_property_read_u32_array(node, "microchip,input-threshold",
- priv->thresholds, priv->model->num_channels)) {
- for (i = 0; i < priv->model->num_channels; i++) {
+ priv->thresholds, priv->model->num_sensor_thresholds)) {
+ for (i = 0; i < priv->model->num_sensor_thresholds; i++) {
if (priv->thresholds[i] > 127) {
dev_err(dev, "Invalid input-threshold value %u\n",
priv->thresholds[i]);
@@ -279,10 +283,12 @@ static int cap11xx_init_keys(struct cap11xx_priv *priv)
of_property_read_u32_array(node, "linux,keycodes",
priv->keycodes, priv->model->num_channels);
- /* Disable autorepeat. The Linux input system has its own handling. */
- error = regmap_write(priv->regmap, CAP11XX_REG_REPEAT_RATE, 0);
- if (error)
- return error;
+ if (priv->model->has_repeat_en) {
+ /* Disable autorepeat. The Linux input system has its own handling. */
+ error = regmap_write(priv->regmap, CAP11XX_REG_REPEAT_RATE, 0);
+ if (error)
+ return error;
+ }
return 0;
}
@@ -301,7 +307,7 @@ static irqreturn_t cap11xx_thread_func(int irq_num, void *data)
if (ret < 0)
goto out;
- ret = regmap_read(priv->regmap, CAP11XX_REG_SENSOR_INPUT, &status);
+ ret = regmap_read(priv->regmap, priv->model->sensor_input_reg_base, &status);
if (ret < 0)
goto out;
@@ -355,7 +361,7 @@ static int cap11xx_led_set(struct led_classdev *cdev,
* 0 (OFF) and 1 (ON).
*/
return regmap_update_bits(priv->regmap,
- CAP11XX_REG_LED_OUTPUT_CONTROL,
+ priv->model->led_output_control_reg_base,
BIT(led->reg),
value ? BIT(led->reg) : 0);
}
@@ -367,6 +373,7 @@ static int cap11xx_init_leds(struct device *dev,
struct cap11xx_led *led;
int cnt = of_get_child_count(node);
int error;
+ u32 duty_val;
if (!num_leds || !cnt)
return 0;
@@ -380,15 +387,18 @@ static int cap11xx_init_leds(struct device *dev,
priv->leds = led;
+ /* Set all LEDs to off */
error = regmap_update_bits(priv->regmap,
- CAP11XX_REG_LED_OUTPUT_CONTROL, 0xff, 0);
+ priv->model->led_output_control_reg_base,
+ GENMASK(min(num_leds, 8) - 1, 0), 0);
if (error)
return error;
+ duty_val = FIELD_PREP(CAP11XX_REG_LED_DUTY_MAX_MASK,
+ CAP11XX_REG_LED_DUTY_MAX_VALUE);
+
error = regmap_update_bits(priv->regmap, CAP11XX_REG_LED_DUTY_CYCLE_4,
- CAP11XX_REG_LED_DUTY_MAX_MASK,
- CAP11XX_REG_LED_DUTY_MAX_VALUE <<
- CAP11XX_REG_LED_DUTY_MAX_MASK_SHIFT);
+ CAP11XX_REG_LED_DUTY_MAX_MASK, duty_val);
if (error)
return error;
@@ -553,41 +563,64 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
}
static const struct cap11xx_hw_model cap1106_model = {
- .product_id = 0x55, .num_channels = 6, .num_leds = 0,
+ .product_id = 0x55,
+ .num_channels = 6, .num_leds = 0, .num_sensor_thresholds = 6,
+ .sensor_input_reg_base = CAP11XX_REG_SENSOR_INPUT,
.has_gain = true,
.has_irq_config = true,
+ .has_repeat_en = true,
};
static const struct cap11xx_hw_model cap1126_model = {
- .product_id = 0x53, .num_channels = 6, .num_leds = 2,
+ .product_id = 0x53,
+ .num_channels = 6, .num_leds = 2, .num_sensor_thresholds = 6,
+ .led_output_control_reg_base = CAP11XX_REG_LED_OUTPUT_CONTROL,
+ .sensor_input_reg_base = CAP11XX_REG_SENSOR_INPUT,
.has_gain = true,
.has_irq_config = true,
+ .has_repeat_en = true,
};
static const struct cap11xx_hw_model cap1188_model = {
- .product_id = 0x50, .num_channels = 8, .num_leds = 8,
+ .product_id = 0x50,
+ .num_channels = 8, .num_leds = 8, .num_sensor_thresholds = 8,
+ .led_output_control_reg_base = CAP11XX_REG_LED_OUTPUT_CONTROL,
+ .sensor_input_reg_base = CAP11XX_REG_SENSOR_INPUT,
.has_gain = true,
.has_irq_config = true,
+ .has_repeat_en = true,
};
static const struct cap11xx_hw_model cap1203_model = {
- .product_id = 0x6d, .num_channels = 3, .num_leds = 0,
+ .product_id = 0x6d,
+ .num_channels = 3, .num_leds = 0, .num_sensor_thresholds = 3,
+ .sensor_input_reg_base = CAP11XX_REG_SENSOR_INPUT,
+ .has_repeat_en = true,
};
static const struct cap11xx_hw_model cap1206_model = {
- .product_id = 0x67, .num_channels = 6, .num_leds = 0,
+ .product_id = 0x67,
+ .num_channels = 6, .num_leds = 0, .num_sensor_thresholds = 6,
+ .sensor_input_reg_base = CAP11XX_REG_SENSOR_INPUT,
+ .has_repeat_en = true,
};
static const struct cap11xx_hw_model cap1293_model = {
- .product_id = 0x6f, .num_channels = 3, .num_leds = 0,
+ .product_id = 0x6f,
+ .num_channels = 3, .num_leds = 0, .num_sensor_thresholds = 3,
+ .sensor_input_reg_base = CAP11XX_REG_SENSOR_INPUT,
.has_gain = true,
+ .has_repeat_en = true,
.has_sensitivity_control = true,
.has_signal_guard = true,
};
static const struct cap11xx_hw_model cap1298_model = {
- .product_id = 0x71, .num_channels = 8, .num_leds = 0,
+ .product_id = 0x71,
+ .num_channels = 8, .num_leds = 0, .num_sensor_thresholds = 8,
+ .sensor_input_reg_base = CAP11XX_REG_SENSOR_INPUT,
.has_gain = true,
+ .has_repeat_en = true,
.has_sensitivity_control = true,
.has_signal_guard = true,
};
--
2.54.0
^ permalink raw reply related
* [PATCH v3 06/10] Input: cap11xx - add reset gpio support
From: Jun Yan @ 2026-06-15 14:20 UTC (permalink / raw)
To: Dmitry Torokhov, Rob Herring, Krzysztof Kozlowski, Conor Dooley
Cc: Jun Yan, linux-input, devicetree, linux-kernel
In-Reply-To: <20260615142103.352163-1-jerrysteve1101@gmail.com>
Some CAP11xx devices (CAP1126/CAP1188) have a dedicated RESET pin.
Add hardware reset operation to improve device reliability and
ensure proper initialization on probe.
Signed-off-by: Jun Yan <jerrysteve1101@gmail.com>
---
drivers/input/keyboard/cap11xx.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index 686174722204..3d75c0f90752 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -5,6 +5,7 @@
* (c) 2014 Daniel Mack <linux@zonque.org>
*/
+#include <linux/delay.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/interrupt.h>
@@ -43,6 +44,9 @@
#define CAP11XX_MANUFACTURER_ID 0x5d
+#define CAP11XX_T_RST_FILT_MIN_US 10000
+#define CAP11XX_T_RST_ON_MIN_MS 400
+
#ifdef CONFIG_LEDS_CLASS
struct cap11xx_led {
struct cap11xx_priv *priv;
@@ -55,6 +59,7 @@ struct cap11xx_priv {
struct regmap *regmap;
struct device *dev;
struct input_dev *idev;
+ struct gpio_desc *reset_gpio;
const struct cap11xx_hw_model *model;
struct cap11xx_led *leds;
@@ -452,6 +457,16 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
if (IS_ERR(priv->regmap))
return PTR_ERR(priv->regmap);
+ priv->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+ if (IS_ERR(priv->reset_gpio))
+ return dev_err_probe(dev, PTR_ERR(priv->reset_gpio),
+ "Failed to get 'reset' GPIO\n");
+ else if (priv->reset_gpio) {
+ usleep_range(CAP11XX_T_RST_FILT_MIN_US, CAP11XX_T_RST_FILT_MIN_US * 2);
+ gpiod_set_value_cansleep(priv->reset_gpio, 0);
+ msleep(CAP11XX_T_RST_ON_MIN_MS);
+ }
+
error = regmap_read(priv->regmap, CAP11XX_REG_PRODUCT_ID, &val);
if (error)
return dev_err_probe(dev, error, "Failed to read product ID\n");
--
2.54.0
^ permalink raw reply related
* [PATCH v3 05/10] dt-bindings: input: microchip,cap11xx: Add reset-gpios property
From: Jun Yan @ 2026-06-15 14:20 UTC (permalink / raw)
To: Dmitry Torokhov, Rob Herring, Krzysztof Kozlowski, Conor Dooley
Cc: Jun Yan, Conor Dooley, linux-input, devicetree, linux-kernel
In-Reply-To: <20260615142103.352163-1-jerrysteve1101@gmail.com>
Add support for the optional reset-gpios property to describe
the active-high reset pin for CAP1126/CAP1188 devices.
Driving the GPIO high asserts reset and deep sleep, while driving
it low releases reset for normal operation.
Restrict this property to be available only on CAP1126 and CAP1188
chips, as other CAP11xx variants do not have a hardware reset pin.
Signed-off-by: Jun Yan <jerrysteve1101@gmail.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
---
.../bindings/input/microchip,cap11xx.yaml | 25 +++++++++++++++++++
1 file changed, 25 insertions(+)
diff --git a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
index 22a292d4a880..778ec6d659a8 100644
--- a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
+++ b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
@@ -49,6 +49,13 @@ properties:
device's ALERT#/CM_IRQ# pin is connected to.
The device only has one interrupt source.
+ reset-gpios:
+ description: |
+ GPIO connected to the active-high RESET pin of the chip;
+ driving it high asserts reset and deep sleep, while driving
+ it low releases reset for normal operation.
+ maxItems: 1
+
autorepeat:
description: |
Enables the Linux input system's autorepeat feature on the input device.
@@ -157,6 +164,20 @@ patternProperties:
allOf:
- $ref: input.yaml
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - microchip,cap1106
+ - microchip,cap1203
+ - microchip,cap1206
+ - microchip,cap1293
+ - microchip,cap1298
+ then:
+ properties:
+ reset-gpios: false
+
- if:
properties:
compatible:
@@ -207,6 +228,8 @@ additionalProperties: false
examples:
- |
+ #include <dt-bindings/gpio/gpio.h>
+
i2c {
#address-cells = <1>;
#size-cells = <0>;
@@ -228,6 +251,8 @@ examples:
<109>, /* KEY_PAGEDOWN */
<104>; /* KEY_PAGEUP */
+ reset-gpios = <&gpio 17 GPIO_ACTIVE_HIGH>;
+
#address-cells = <1>;
#size-cells = <0>;
--
2.54.0
^ permalink raw reply related
* [PATCH v3 04/10] dt-bindings: input: microchip,cap11xx: Add microchip,cap1126 LED reg constraints
From: Jun Yan @ 2026-06-15 14:20 UTC (permalink / raw)
To: Dmitry Torokhov, Rob Herring, Krzysztof Kozlowski, Conor Dooley
Cc: Jun Yan, linux-input, devicetree, linux-kernel
In-Reply-To: <20260615142103.352163-1-jerrysteve1101@gmail.com>
Apply per-chip LED channel limits:
- CAP1126: max 2 channels (0-1)
- CAP1188: max 8 channels (0-7)
- CAP1106, CAP12xx: no LED support
Signed-off-by: Jun Yan <jerrysteve1101@gmail.com>
---
.../bindings/input/microchip,cap11xx.yaml | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
index 9578c7c206a2..22a292d4a880 100644
--- a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
+++ b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
@@ -171,6 +171,19 @@ allOf:
patternProperties:
"^led@": false
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - microchip,cap1126
+ then:
+ patternProperties:
+ "^led@":
+ properties:
+ reg:
+ maximum: 1
+
- if:
properties:
compatible:
--
2.54.0
^ permalink raw reply related
* [PATCH v3 03/10] dt-bindings: input: microchip,cap11xx: Update datasheet URL and LED reg range
From: Jun Yan @ 2026-06-15 14:20 UTC (permalink / raw)
To: Dmitry Torokhov, Rob Herring, Krzysztof Kozlowski, Conor Dooley
Cc: Jun Yan, linux-input, devicetree, linux-kernel
In-Reply-To: <20260615142103.352163-1-jerrysteve1101@gmail.com>
- Add datasheet links for all supported CAP11xx variants.
- Update LED node regex and replace enum constraints with minimum/maximum
for LED reg ranges in preparation for CAP1114 support.
CAP1114 has 11 LED channels. minimum/maximum constraints are easier to
maintain than long enum lists when expanding channel count later.
Signed-off-by: Jun Yan <jerrysteve1101@gmail.com>
---
.../bindings/input/microchip,cap11xx.yaml | 17 ++++++++++++++---
1 file changed, 14 insertions(+), 3 deletions(-)
diff --git a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
index 7ade03f1b32b..9578c7c206a2 100644
--- a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
+++ b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml
@@ -10,6 +10,15 @@ description: |
The Microchip CAP1xxx Family of RightTouchTM multiple-channel capacitive
touch controllers and LED drivers. The device communication via I2C only.
+ For more product information please see the links below:
+ CAP1106: https://ww1.microchip.com/downloads/en/DeviceDoc/00001624B.pdf
+ CAP1126: https://ww1.microchip.com/downloads/en/DeviceDoc/00001623B.pdf
+ CAP1188: https://ww1.microchip.com/downloads/en/DeviceDoc/00001620C.pdf
+ CAP1203: https://ww1.microchip.com/downloads/en/DeviceDoc/00001572B.pdf
+ CAP1206: https://ww1.microchip.com/downloads/en/DeviceDoc/00001567B.pdf
+ CAP1293: https://ww1.microchip.com/downloads/en/DeviceDoc/00001566B.pdf
+ CAP1298: https://ww1.microchip.com/downloads/en/DeviceDoc/00001571B.pdf
+
maintainers:
- Rob Herring <robh@kernel.org>
@@ -124,14 +133,16 @@ properties:
The number of entries must correspond to the number of channels.
patternProperties:
- "^led@[0-7]$":
+ "^led@[0-9a-f]$":
type: object
description: CAP11xx LEDs
$ref: /schemas/leds/common.yaml#
properties:
reg:
- enum: [0, 1, 2, 3, 4, 5, 6, 7]
+ description: LED channel number
+ minimum: 0
+ maximum: 7
label: true
@@ -158,7 +169,7 @@ allOf:
- microchip,cap1298
then:
patternProperties:
- "^led@[0-7]$": false
+ "^led@": false
- if:
properties:
--
2.54.0
^ permalink raw reply related
* [PATCH v3 02/10] Input: cap11xx - remove unused register macros
From: Jun Yan @ 2026-06-15 14:20 UTC (permalink / raw)
To: Dmitry Torokhov, Rob Herring, Krzysztof Kozlowski, Conor Dooley
Cc: Jun Yan, linux-input, devicetree, linux-kernel
In-Reply-To: <20260615142103.352163-1-jerrysteve1101@gmail.com>
Remove unused register address macros and unused definitions in
the cap11xx_reg_defaults array and cap11xx_volatile_reg.
This cleanup reduces code clutter and makes the driver easier to
maintain without affecting functionality.
Signed-off-by: Jun Yan <jerrysteve1101@gmail.com>
---
drivers/input/keyboard/cap11xx.c | 58 --------------------------------
1 file changed, 58 deletions(-)
diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index 485d8ba97723..686174722204 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -20,53 +20,23 @@
#define CAP11XX_REG_MAIN_CONTROL_GAIN_SHIFT (6)
#define CAP11XX_REG_MAIN_CONTROL_GAIN_MASK (0xc0)
#define CAP11XX_REG_MAIN_CONTROL_DLSEEP BIT(4)
-#define CAP11XX_REG_GENERAL_STATUS 0x02
#define CAP11XX_REG_SENSOR_INPUT 0x03
-#define CAP11XX_REG_NOISE_FLAG_STATUS 0x0a
-#define CAP11XX_REG_SENOR_DELTA(X) (0x10 + (X))
#define CAP11XX_REG_SENSITIVITY_CONTROL 0x1f
#define CAP11XX_REG_SENSITIVITY_CONTROL_DELTA_SENSE_MASK 0x70
-#define CAP11XX_REG_CONFIG 0x20
-#define CAP11XX_REG_SENSOR_ENABLE 0x21
-#define CAP11XX_REG_SENSOR_CONFIG 0x22
-#define CAP11XX_REG_SENSOR_CONFIG2 0x23
-#define CAP11XX_REG_SAMPLING_CONFIG 0x24
-#define CAP11XX_REG_CALIBRATION 0x26
-#define CAP11XX_REG_INT_ENABLE 0x27
#define CAP11XX_REG_REPEAT_RATE 0x28
#define CAP11XX_REG_SIGNAL_GUARD_ENABLE 0x29
-#define CAP11XX_REG_MT_CONFIG 0x2a
-#define CAP11XX_REG_MT_PATTERN_CONFIG 0x2b
-#define CAP11XX_REG_MT_PATTERN 0x2d
-#define CAP11XX_REG_RECALIB_CONFIG 0x2f
#define CAP11XX_REG_SENSOR_THRESH(X) (0x30 + (X))
-#define CAP11XX_REG_SENSOR_NOISE_THRESH 0x38
-#define CAP11XX_REG_STANDBY_CHANNEL 0x40
-#define CAP11XX_REG_STANDBY_CONFIG 0x41
-#define CAP11XX_REG_STANDBY_SENSITIVITY 0x42
-#define CAP11XX_REG_STANDBY_THRESH 0x43
#define CAP11XX_REG_CONFIG2 0x44
#define CAP11XX_REG_CONFIG2_ALT_POL BIT(6)
-#define CAP11XX_REG_SENSOR_BASE_CNT(X) (0x50 + (X))
-#define CAP11XX_REG_LED_POLARITY 0x73
#define CAP11XX_REG_LED_OUTPUT_CONTROL 0x74
#define CAP11XX_REG_CALIB_SENSITIVITY_CONFIG 0x80
#define CAP11XX_REG_CALIB_SENSITIVITY_CONFIG2 0x81
-
-#define CAP11XX_REG_LED_DUTY_CYCLE_1 0x90
-#define CAP11XX_REG_LED_DUTY_CYCLE_2 0x91
-#define CAP11XX_REG_LED_DUTY_CYCLE_3 0x92
#define CAP11XX_REG_LED_DUTY_CYCLE_4 0x93
-#define CAP11XX_REG_LED_DUTY_MIN_MASK (0x0f)
-#define CAP11XX_REG_LED_DUTY_MIN_MASK_SHIFT (0)
#define CAP11XX_REG_LED_DUTY_MAX_MASK (0xf0)
#define CAP11XX_REG_LED_DUTY_MAX_MASK_SHIFT (4)
#define CAP11XX_REG_LED_DUTY_MAX_VALUE (15)
-#define CAP11XX_REG_SENSOR_CALIB (0xb1 + (X))
-#define CAP11XX_REG_SENSOR_CALIB_LSB1 0xb9
-#define CAP11XX_REG_SENSOR_CALIB_LSB2 0xba
#define CAP11XX_REG_PRODUCT_ID 0xfd
#define CAP11XX_REG_MANUFACTURER_ID 0xfe
#define CAP11XX_REG_REVISION 0xff
@@ -111,37 +81,15 @@ struct cap11xx_hw_model {
static const struct reg_default cap11xx_reg_defaults[] = {
{ CAP11XX_REG_MAIN_CONTROL, 0x00 },
- { CAP11XX_REG_GENERAL_STATUS, 0x00 },
- { CAP11XX_REG_SENSOR_INPUT, 0x00 },
- { CAP11XX_REG_NOISE_FLAG_STATUS, 0x00 },
{ CAP11XX_REG_SENSITIVITY_CONTROL, 0x2f },
- { CAP11XX_REG_CONFIG, 0x20 },
- { CAP11XX_REG_SENSOR_ENABLE, 0x3f },
- { CAP11XX_REG_SENSOR_CONFIG, 0xa4 },
- { CAP11XX_REG_SENSOR_CONFIG2, 0x07 },
- { CAP11XX_REG_SAMPLING_CONFIG, 0x39 },
- { CAP11XX_REG_CALIBRATION, 0x00 },
- { CAP11XX_REG_INT_ENABLE, 0x3f },
{ CAP11XX_REG_REPEAT_RATE, 0x3f },
- { CAP11XX_REG_MT_CONFIG, 0x80 },
- { CAP11XX_REG_MT_PATTERN_CONFIG, 0x00 },
- { CAP11XX_REG_MT_PATTERN, 0x3f },
- { CAP11XX_REG_RECALIB_CONFIG, 0x8a },
{ CAP11XX_REG_SENSOR_THRESH(0), 0x40 },
{ CAP11XX_REG_SENSOR_THRESH(1), 0x40 },
{ CAP11XX_REG_SENSOR_THRESH(2), 0x40 },
{ CAP11XX_REG_SENSOR_THRESH(3), 0x40 },
{ CAP11XX_REG_SENSOR_THRESH(4), 0x40 },
{ CAP11XX_REG_SENSOR_THRESH(5), 0x40 },
- { CAP11XX_REG_SENSOR_NOISE_THRESH, 0x01 },
- { CAP11XX_REG_STANDBY_CHANNEL, 0x00 },
- { CAP11XX_REG_STANDBY_CONFIG, 0x39 },
- { CAP11XX_REG_STANDBY_SENSITIVITY, 0x02 },
- { CAP11XX_REG_STANDBY_THRESH, 0x40 },
{ CAP11XX_REG_CONFIG2, 0x40 },
- { CAP11XX_REG_LED_POLARITY, 0x00 },
- { CAP11XX_REG_SENSOR_CALIB_LSB1, 0x00 },
- { CAP11XX_REG_SENSOR_CALIB_LSB2, 0x00 },
};
static bool cap11xx_volatile_reg(struct device *dev, unsigned int reg)
@@ -149,12 +97,6 @@ static bool cap11xx_volatile_reg(struct device *dev, unsigned int reg)
switch (reg) {
case CAP11XX_REG_MAIN_CONTROL:
case CAP11XX_REG_SENSOR_INPUT:
- case CAP11XX_REG_SENOR_DELTA(0):
- case CAP11XX_REG_SENOR_DELTA(1):
- case CAP11XX_REG_SENOR_DELTA(2):
- case CAP11XX_REG_SENOR_DELTA(3):
- case CAP11XX_REG_SENOR_DELTA(4):
- case CAP11XX_REG_SENOR_DELTA(5):
return true;
}
--
2.54.0
^ permalink raw reply related
* [PATCH v3 01/10] Input: cap11xx - clean up duplicate log and add probe error logs
From: Jun Yan @ 2026-06-15 14:20 UTC (permalink / raw)
To: Dmitry Torokhov, Rob Herring, Krzysztof Kozlowski, Conor Dooley
Cc: Jun Yan, linux-input, devicetree, linux-kernel
In-Reply-To: <20260615142103.352163-1-jerrysteve1101@gmail.com>
Duplicated device detection log exists at line 537 and line 542,
which brings redundant kernel print messages. Drop one redundant
log entry to clean up dmesg output.
Meanwhile add missing error logs when I2C communication fails
during driver probe(), helping debug.
Signed-off-by: Jun Yan <jerrysteve1101@gmail.com>
---
drivers/input/keyboard/cap11xx.c | 11 ++++-------
1 file changed, 4 insertions(+), 7 deletions(-)
diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index 2447c1ae2166..485d8ba97723 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -512,7 +512,7 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
error = regmap_read(priv->regmap, CAP11XX_REG_PRODUCT_ID, &val);
if (error)
- return error;
+ return dev_err_probe(dev, error, "Failed to read product ID\n");
if (val != cap->product_id) {
dev_err(dev, "Product ID: Got 0x%02x, expected 0x%02x\n",
@@ -522,7 +522,7 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
error = regmap_read(priv->regmap, CAP11XX_REG_MANUFACTURER_ID, &val);
if (error)
- return error;
+ return dev_err_probe(dev, error, "Failed to read manufacturer ID\n");
if (val != CAP11XX_MANUFACTURER_ID) {
dev_err(dev, "Manufacturer ID: Got 0x%02x, expected 0x%02x\n",
@@ -531,11 +531,8 @@ static int cap11xx_i2c_probe(struct i2c_client *i2c_client)
}
error = regmap_read(priv->regmap, CAP11XX_REG_REVISION, &rev);
- if (error < 0)
- return error;
-
- dev_info(dev, "CAP11XX detected, model %s, revision 0x%02x\n",
- id->name, rev);
+ if (error)
+ return dev_err_probe(dev, error, "Failed to read revision\n");
priv->model = cap;
--
2.54.0
^ permalink raw reply related
* [PATCH v3 00/10] Input: cap11xx - Add support for CAP1114
From: Jun Yan @ 2026-06-15 14:20 UTC (permalink / raw)
To: Dmitry Torokhov, Rob Herring, Krzysztof Kozlowski, Conor Dooley
Cc: Jun Yan, linux-input, devicetree, linux-kernel
CAP1114 is a 14-channel capacitive touch sensor with 11 LED outputs
and hardware reset support.
Patches 1-4 perform driver cleanup and DT binding tweaks.
Patches 5-6 add reset-gpios support for CAP11xx.
Patches 7-10 add support for CAP1114.
Changes in v3:
- Simplified the logic of the reset pin operation.
- Adjust linux,keycodes configuration for CAP11xx.
- Drop unnecessary CAP11XX_REG_SENSOR_THRESH(8).
- Checks for the presence of microchip,calib-sensitivity and
microchip,signal-guard properties before processing them.
- Link to v2:
https://lore.kernel.org/all/20260612072237.1177304-1-jerrysteve1101@gmail.com/
Changes in v2:
- Drop LED property tweaks, keep only reg changes and node regex
update in DT bindings.
- Split microchip,cap1126 LED reg constraints into a separate patch.
- Replace usleep_range() with msleep() for 500 ms delay during
reset pin handling.
- Add missing <linux/delay.h> for usleep_range() and msleep().
- Add CAP1114 to unsupported enum for microchip,signal-guard and
microchip,calib-sensitivity
- Add constraint for linux,keycodes to support CAP1114.
- When reading CAP1114 button status, mask STATUS1 to bits 0-5
and OR with STATUS2.
- Adjust code style.
- Link to v1:
https://lore.kernel.org/all/20260606150458.250606-1-jerrysteve1101@gmail.com
Jun Yan (10):
Input: cap11xx - clean up duplicate log and add probe error logs
Input: cap11xx - remove unused register macros
dt-bindings: input: microchip,cap11xx: Update datasheet URL and LED
reg range
dt-bindings: input: microchip,cap11xx: Add microchip,cap1126 LED reg
constraints
dt-bindings: input: microchip,cap11xx: Add reset-gpios property
Input: cap11xx - add reset gpio support
Input: cap11xx - refactor code for better CAP1114 support.
Input: cap11xx - guard unsupported DT properties before parsing
dt-bindings: input: microchip,cap11xx: Add CAP1114 support
Input: cap11xx - add support for CAP1114
.../bindings/input/microchip,cap11xx.yaml | 90 +++++-
drivers/input/keyboard/cap11xx.c | 280 +++++++++++-------
2 files changed, 253 insertions(+), 117 deletions(-)
--
2.54.0
^ permalink raw reply
* Re: [PATCH 2/9] iio: orientation: hid-sensor-incl-3d: Fix race between callback registration and device exposure
From: Pandruvada, Srinivas @ 2026-06-15 13:36 UTC (permalink / raw)
To: jic23@kernel.org
Cc: dlechner@baylibre.com, archana.patni@linux.intel.com,
hongyan.song@intel.com, linux-iio@vger.kernel.org,
nuno.sa@analog.com, linux-kernel@vger.kernel.org,
jikos@kernel.org, andy@kernel.org, sanjayembeddedse@gmail.com,
linux-input@vger.kernel.org
In-Reply-To: <20260614192442.6eaa1a54@jic23-huawei>
On Sun, 2026-06-14 at 19:24 +0100, Jonathan Cameron wrote:
> On Mon, 8 Jun 2026 15:34:05 +0000
> "Pandruvada, Srinivas" <srinivas.pandruvada@intel.com> wrote:
>
> > On Sat, 2026-06-06 at 17:07 +0530, Sanjay Chitroda wrote:
> > > From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
> > >
> > > The driver registers the IIO device before completing sensor hub
> > > callback registration and unregisters callbacks while the IIO
> > > device
> > > is still exposed during teardown.
> > >
> > > This creates race windows in both probe and remove paths, which
> > > can
> > > lead to NULL pointer dereferences or use-after-free.
> >
> > Reordering is fine, but can you show how this use after free is
> > possible?
> Agreed - I'm not seeing a definite issue so more info needed.
> For now I'm going to mark this changes-requested in patchwork.
>
> It might be a touch slow if someone manages to get buffered capture
> up before the callbacks are available, but I think that just means
> dropping a few samples?
Correct.
Thanks,
Srinivas
>
> Jonathan
>
> >
> > Thanks,
> > Srinivas
>
^ permalink raw reply
* Re: [PATCH] HID: hidpp: fix potential UAF in hidpp_connect_event()
From: sashiko-bot @ 2026-06-15 13:12 UTC (permalink / raw)
To: Jiri Kosina; +Cc: dmitry.torokhov, linux-input
In-Reply-To: <qq420675-14n0-p23s-10oo-1n8113s2nq22@xreary.bet>
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
Pre-existing issues:
- [Critical] Dangling pointer Use-After-Free when `input_register_device()` fails during synchronous probe via `hid_connect()`.
- [High] Time-of-Check to Time-of-Use (TOCTOU) race condition leading to a Use-After-Free.
--
commit 958cf4bb8a3ce7336c278ac4fb346b928f5fe9b9
Author: Jiri Kosina <jikos@kernel.org>
HID: hidpp: fix potential UAF in hidpp_connect_event()
If input_register_device() fails, we call input_free_device(), but keep
stale pointer to the old device in hidpp->input, which could potentially
lead to UAF. Fix that by resetting it to NULL before returning from
hidpp_connect_event().
Reported-by: zdi-disclosures@trendmicro.com
Signed-off-by: Jiri Kosina <jkosina@suse.com>
> diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
> index ccbf28869a968..d8e86b6ccf375 100644
> --- a/drivers/hid/hid-logitech-hidpp.c
> +++ b/drivers/hid/hid-logitech-hidpp.c
> @@ -4295,6 +4295,7 @@ static void hidpp_connect_event(struct work_struct *work)
>
> ret = input_register_device(input);
> if (ret) {
> + hidpp->input = NULL;
[Severity: High]
This is a pre-existing issue, but does this clear the shared state too late to
prevent a race condition?
Since hidpp_connect_event() runs asynchronously in a workqueue, hardware
events can be processed concurrently in interrupt context. The allocated
device pointer is published to the global hidpp->input state via
hidpp_populate_input() before the registration attempt.
A concurrent raw event could read hidpp->input and pass the safety check:
drivers/hid/hid-logitech-hidpp.c:wtp_raw_event() {
if (!wd || !hidpp->input)
return 1;
}
If input_register_device() then fails, the error path clears hidpp->input
and frees the memory locklessly.
Could the concurrent raw event handler, already past the safety check,
access the freed memory and cause a use-after-free?
> input_free_device(input);
> return;
[Severity: Critical]
This is also a pre-existing issue, but does a similar dangling pointer remain
if registration fails during synchronous probe?
While this patch addresses a dangling pointer in hidpp_connect_event(), a
similar situation appears to exist in the hid core connection path. For
non-delayed devices, hidinput_connect() calls hidpp_input_configured(),
which caches hidinput->input into hidpp->input:
drivers/hid/hid-logitech-hidpp.c:hidpp_input_configured() {
hidpp_populate_input(hidpp, input);
}
Immediately after, hidinput_connect() calls input_register_device(). If
registration fails, the error path frees the device:
drivers/hid/hid-input.c:hidinput_connect() {
if (input_register_device(hidinput->input))
goto out_unwind;
}
Because hid_connect() ignores the hidinput_connect() failure when the
driver has a raw_event handler, probe succeeds and the device remains active.
Would incoming hardware events then trigger hidpp_raw_event(), successfully
pass the check against hidpp->input, and dereference the freed pointer?
> }
--
Sashiko AI review · https://sashiko.dev/#/patchset/qq420675-14n0-p23s-10oo-1n8113s2nq22@xreary.bet?part=1
^ permalink raw reply
* [PATCH] HID: hidpp: fix potential UAF in hidpp_connect_event()
From: Jiri Kosina @ 2026-06-15 12:58 UTC (permalink / raw)
To: Benjamin Tissoires; +Cc: linux-kernel, linux-input
From: Jiri Kosina <jkosina@suse.com>
If input_register_device() fails, we call input_free_device(), but keep
stale pointer to the old device in hidpp->input, which could potentially
lead to UAF. Fix that by resetting it to NULL before returning from
hidpp_connect_event().
Reported-by: zdi-disclosures@trendmicro.com
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
v1->v2: set hidpp->input to NULL before freeing the device to avoid race
as reported by Sashiko
drivers/hid/hid-logitech-hidpp.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index ccbf28869a96..d8e86b6ccf37 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -4295,6 +4295,7 @@ static void hidpp_connect_event(struct work_struct *work)
ret = input_register_device(input);
if (ret) {
+ hidpp->input = NULL;
input_free_device(input);
return;
}
--
Jiri Kosina
SUSE Labs
^ permalink raw reply related
* Re: [PATCH 05/10] [v2] mips: select legacy gpiolib interfaces where used
From: Thomas Bogendoerfer @ 2026-06-15 10:33 UTC (permalink / raw)
To: Arnd Bergmann
Cc: linux-gpio, linux-kernel, Arnd Bergmann, Christian Lamparter,
Johannes Berg, Aaro Koskinen, Andreas Kemnade, Kevin Hilman,
Roger Quadros, Tony Lindgren, John Paul Adrian Glaubitz,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86,
H. Peter Anvin, Linus Walleij, Bartosz Golaszewski,
Dmitry Torokhov, Lee Jones, Pavel Machek, Matti Vaittinen,
Florian Fainelli, Jonas Gorski, Andrew Lunn, Vladimir Oltean,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
linux-wireless, linux-omap, linux-arm-kernel, linux-mips,
linux-sh, linux-input, linux-leds, netdev, Bartosz Golaszewski
In-Reply-To: <20260520183815.2510387-6-arnd@kernel.org>
On Wed, May 20, 2026 at 08:38:10PM +0200, Arnd Bergmann wrote:
> From: Arnd Bergmann <arnd@arndb.de>
>
> A few old machines have not been converted away from the old-style
> gpiolib interfaces. Make these select the new CONFIG_GPIOLIB_LEGACY
> symbol so the code still works where it is needed but can be left
> out otherwise.
>
> This is the list of all gpio_request() calls in mips:
>
> arch/mips/alchemy/devboards/db1000.c: gpio_request(19, "sd0_cd");
> arch/mips/alchemy/devboards/db1000.c: gpio_request(20, "sd1_cd");
> arch/mips/alchemy/devboards/db1200.c: gpio_request(215, "otg-vbus");
> arch/mips/bcm47xx/workarounds.c: err = gpio_request_one(usb_power, GPIOF_OUT_INIT_HIGH, "usb_power");
> arch/mips/bcm63xx/boards/board_bcm963xx.c: gpio_request_one(board.ephy_reset_gpio,
> arch/mips/txx9/rbtx4927/setup.c: gpio_request(15, "sio-dtr");
>
> Most of these should be easy enough to change to modern gpio descriptors
> or remove if they are no longer in use.
>
> Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
> Reviewed-by: Linus Walleij <linusw@kernel.org>
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
> ---
> v2: no changes. There was no discussion on this, but the patch
> has so far not made it into the linux-mips tree, so I'm including
> it for completeness.
> ---
> arch/mips/Kconfig | 5 +++++
> arch/mips/alchemy/Kconfig | 1 -
> arch/mips/txx9/Kconfig | 1 +
> 3 files changed, 6 insertions(+), 1 deletion(-)
applied to mips-next
Thomas.
--
Crap can work. Given enough thrust pigs will fly, but it's not necessarily a
good idea. [ RFC1925, 2.3 ]
^ permalink raw reply
* Re: [PATCH v3 2/4] Input: snvs_pwrkey - replace hardcoding -EINVAL with original error code
From: sashiko-bot @ 2026-06-15 7:58 UTC (permalink / raw)
To: joy.zou; +Cc: Frank.Li, imx, linux-input, dmitry.torokhov
In-Reply-To: <20260615-b4-pwrkey-v3-2-9510b1173f6e@oss.nxp.com>
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
Pre-existing issues:
- [High] Missing cleanup for dev_pm_set_wake_irq() causes memory leak and state corruption on driver unbind.
- [High] Systematic failure to check regmap_read() return values leads to consuming uninitialized stack memory, risking spurious system shutdown.
--
commit d2ee00e9f90457779e6f0d87a01d54e5af524f82
Author: Joy Zou <joy.zou@nxp.com>
Input: snvs_pwrkey - replace hardcoding -EINVAL with original error code
This commit replaces a hardcoded -EINVAL with the actual error code returned
by platform_get_irq(). This preserves valuable diagnostic information and
allows probe deferral (-EPROBE_DEFER) to work correctly.
> diff --git a/drivers/input/keyboard/snvs_pwrkey.c b/drivers/input/keyboard/snvs_pwrkey.c
> index 748196fcce75b..a291812e6d22e 100644
> --- a/drivers/input/keyboard/snvs_pwrkey.c
> +++ b/drivers/input/keyboard/snvs_pwrkey.c
> @@ -148,7 +148,7 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
>
> pdata->irq = platform_get_irq(pdev, 0);
> if (pdata->irq < 0)
> - return -EINVAL;
> + return pdata->irq;
>
> error = of_property_read_u32(np, "power-off-time-sec", &val);
> if (!error) {
[ ... ]
[Severity: High]
This is a pre-existing issue, but I noticed a potential lifecycle regression
further down in imx_snvs_pwrkey_probe():
drivers/input/keyboard/snvs_pwrkey.c:imx_snvs_pwrkey_probe() {
...
error = dev_pm_set_wake_irq(dev, pdata->irq);
if (error)
dev_err(dev, "irq wake enable failed.\n");
...
}
The driver configures a wake IRQ using dev_pm_set_wake_irq(), which
allocates a wake_irq structure and attaches it to dev->power.wakeirq.
However, there doesn't appear to be a paired remove callback to call
dev_pm_clear_wake_irq() during driver unbind.
Does this permanently leak memory if the driver is unbound via sysfs?
Additionally, since the underlying IRQ is managed by devm_request_irq(), it
will be freed on unbind while dev->power.wakeirq remains configured. If the
system later attempts to suspend, could the PM core evaluate
device_may_wakeup() (which remains true since device_init_wakeup() isn't
reverted) and call enable_irq_wake() on a freed IRQ?
[ ... ]
[Severity: High]
This isn't a bug introduced by this patch, but I also noticed that
regmap_read() return values are not checked in several places before
consuming the variables passed by reference:
drivers/input/keyboard/snvs_pwrkey.c:imx_snvs_pwrkey_interrupt() {
...
u32 lp_status;
pm_wakeup_event(input->dev.parent, 0);
regmap_read(pdata->snvs, SNVS_LPSR_REG, &lp_status);
if (lp_status & SNVS_LPSR_SPO) {
...
}
It also happens in the timer handler:
drivers/input/keyboard/snvs_pwrkey.c:imx_imx_snvs_check_for_events() {
...
u32 state;
regmap_read(pdata->snvs, SNVS_HPSR_REG, &state);
state = state & SNVS_HPSR_BTN ? 1 : 0;
...
}
If regmap_read() fails (e.g., due to an underlying clock enable failure or
MMIO bus error), it returns an error code and leaves the target stack
variables (lp_status, state) uninitialized.
Since these uninitialized stack variables are then used in logic checks,
could this lead to unpredictable behavior? For example, in the interrupt
and timer handlers, if the uninitialized stack memory randomly has the
SNVS_LPSR_SPO or SNVS_HPSR_BTN bits set, would this trigger a spurious
KEY_POWER event and an unintended system shutdown?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260615-b4-pwrkey-v3-0-9510b1173f6e@oss.nxp.com?part=2
^ permalink raw reply
* Re: [PATCH v3 1/4] Input: snvs_pwrkey - make use of dev_err_probe()
From: sashiko-bot @ 2026-06-15 7:57 UTC (permalink / raw)
To: joy.zou; +Cc: linux-input, Frank.Li, dmitry.torokhov, imx
In-Reply-To: <20260615-b4-pwrkey-v3-1-9510b1173f6e@oss.nxp.com>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [Medium] Missing `.remove` callback causes a leak of `struct wake_irq` and leaves dangling wakeup configuration upon driver unbind.
--
commit 07567ee0ff85afeb83d7fcfa00735130f4ec77e0
Author: Joy Zou <joy.zou@nxp.com>
Input: snvs_pwrkey - make use of dev_err_probe()
This commit updates the imx_snvs_pwrkey_probe function to use dev_err_probe
for its error paths. This helps simplify error logging and properly handles
probe deferral conditions.
> diff --git a/drivers/input/keyboard/snvs_pwrkey.c b/drivers/input/keyboard/snvs_pwrkey.c
> --- a/drivers/input/keyboard/snvs_pwrkey.c
> +++ b/drivers/input/keyboard/snvs_pwrkey.c
[ ... ]
> @@ -209,16 +203,12 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
> error = devm_request_irq(&pdev->dev, pdata->irq,
> imx_snvs_pwrkey_interrupt,
> 0, pdev->name, pdev);
> - if (error) {
> - dev_err(&pdev->dev, "interrupt not available.\n");
> - return error;
> - }
> + if (error)
> + return dev_err_probe(&pdev->dev, error, "interrupt not available.\n");
>
> error = input_register_device(input);
> - if (error < 0) {
> - dev_err(&pdev->dev, "failed to register input device\n");
> - return error;
> - }
> + if (error < 0)
> + return dev_err_probe(&pdev->dev, error, "failed to register input device\n");
>
> device_init_wakeup(&pdev->dev, pdata->wakeup);
> error = dev_pm_set_wake_irq(&pdev->dev, pdata->irq);
[Severity: Medium]
This is a pre-existing issue, but I noticed there might be a resource cleanup
issue here in imx_snvs_pwrkey_probe().
Does this code leak the wakeup resources when the driver is unbound?
It appears that device_init_wakeup() and dev_pm_set_wake_irq() allocate
unmanaged resources and attach them to the device. Because there is no remove
callback or managed action to clean them up via dev_pm_clear_wake_irq() and
device_init_wakeup(dev, false), these resources might be leaked on unbind.
If the driver is later re-bound, could this also cause probe to fail since
dev_pm_attach_wake_irq() returns -EEXIST when the wakeirq is already
initialized?
Would it be appropriate to switch these to devm_device_init_wakeup() and
devm_pm_set_wake_irq() to handle the cleanup automatically?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260615-b4-pwrkey-v3-0-9510b1173f6e@oss.nxp.com?part=1
^ permalink raw reply
* Re: [PATCH v3 3/4] Input: snvs_pwrkey - use local device pointer to simple code
From: sashiko-bot @ 2026-06-15 7:57 UTC (permalink / raw)
To: joy.zou; +Cc: linux-input, Frank.Li, imx, dmitry.torokhov
In-Reply-To: <20260615-b4-pwrkey-v3-3-9510b1173f6e@oss.nxp.com>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [High] The driver calls `dev_pm_set_wake_irq()` but does not use the `devm_` variant or provide a `.remove` function, leading to a resource leak and potentially broken system suspend on driver unbind.
--
commit d7d5ed812213c739d1459c472b4e230aac0a6e8d
Author: Joy Zou <joy.zou@nxp.com>
Input: snvs_pwrkey - use local device pointer to simple code
This commit introduces a local struct device pointer in the probe function
to reduce boilerplate code when referencing the platform device. It is
intended to be a non-functional change.
> diff --git a/drivers/input/keyboard/snvs_pwrkey.c b/drivers/input/keyboard/snvs_pwrkey.c
> --- a/drivers/input/keyboard/snvs_pwrkey.c
> +++ b/drivers/input/keyboard/snvs_pwrkey.c
[ ... ]
> @@ -193,27 +194,27 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
[ ... ]
> - device_init_wakeup(&pdev->dev, pdata->wakeup);
> - error = dev_pm_set_wake_irq(&pdev->dev, pdata->irq);
> + device_init_wakeup(dev, pdata->wakeup);
> + error = dev_pm_set_wake_irq(dev, pdata->irq);
[Severity: High]
This is a pre-existing issue, but does this leak the wake IRQ on driver
unbind?
Looking at imx_snvs_pwrkey_probe() in drivers/input/keyboard/snvs_pwrkey.c,
the driver configures the wake IRQ using dev_pm_set_wake_irq() but it does
not use the devm_ variant, nor does it provide a .remove callback to call
dev_pm_clear_wake_irq().
When the driver unbinds, devres automatically frees the IRQ, but the memory
for the wake IRQ structure remains allocated and attached to
dev->power.wakeirq.
Will a subsequent system suspend then attempt to call enable_irq_wake() on a
freed IRQ number? Also, if the driver is later re-bound, would it trigger a
warning in dev_pm_attach_wake_irq() because dev->power.wakeirq is already
initialized?
Should this be updated to use devm_pm_set_wake_irq() instead?
> if (error)
> - dev_err(&pdev->dev, "irq wake enable failed.\n");
> + dev_err(dev, "irq wake enable failed.\n");
>
> return 0;
> }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260615-b4-pwrkey-v3-0-9510b1173f6e@oss.nxp.com?part=3
^ permalink raw reply
* [PATCH v3 4/4] Input: snvs_pwrkey - report press event in interrupt handler
From: joy.zou @ 2026-06-15 7:52 UTC (permalink / raw)
To: Dmitry Torokhov, Frank Li, Bough Chen, Peng Fan, Jacky Bai, Ye Li
Cc: Joy Zou, imx, linux-input, linux-kernel, Joy Zou
In-Reply-To: <20260615-b4-pwrkey-v3-0-9510b1173f6e@oss.nxp.com>
From: Joy Zou <joy.zou@nxp.com>
The driver implements debounce protection using a timer-based mechanism:
when a key interrupt occurs, a timer is scheduled to verify the key state
after DEBOUNCE_TIME before reporting the event. This works well during
normal operation.
However, key press events can be lost during system resume on platforms
like i.MX8MQ-EVK because:
1. During the no_irq resume phase, PCIe driver restoration can take up to
200ms with IRQs disabled.
2. The power key interrupt remains pending during the no_irq phase.
3. If the key is released before IRQs are re-enabled, the timer eventually
runs but sees the key as released and skips reporting the event.
Report key press events directly in interrupt handler to prevent event
loss during system suspend. This is safe because:
1. Only one event is reported per suspend cycle.
2. Normal operation retains the existing timer-based debounce mechanism.
Signed-off-by: Joy Zou <joy.zou@nxp.com>
---
Changes for v3:
1. Add spinlock for pdata->keystate and pdata->suspended per AI review
comments.
2. Replace hardcode value 1 with local variable keystate in input_report_key()
under suspended.
Changes for v2:
1. Add a boolean variable suspended and PM callback functions to replace
the use of the is_suspended field per AI review comments.
2. Move event report handle to else branch in suspended state, since the
pdata->minor_rev == 0 branch has no debounce detection per AI review
comments.
3. Modify the commit message.
---
drivers/input/keyboard/snvs_pwrkey.c | 60 ++++++++++++++++++++++++++++++++++--
1 file changed, 57 insertions(+), 3 deletions(-)
diff --git a/drivers/input/keyboard/snvs_pwrkey.c b/drivers/input/keyboard/snvs_pwrkey.c
index 4a1d04898482..d6ea3c2d87c6 100644
--- a/drivers/input/keyboard/snvs_pwrkey.c
+++ b/drivers/input/keyboard/snvs_pwrkey.c
@@ -39,6 +39,8 @@ struct pwrkey_drv_data {
int keycode;
int keystate; /* 1:pressed */
int wakeup;
+ bool suspended; /* Track suspend state */
+ spinlock_t lock; /* Protects keystate and suspended */
struct timer_list check_timer;
struct input_dev *input;
u8 minor_rev;
@@ -49,14 +51,21 @@ static void imx_imx_snvs_check_for_events(struct timer_list *t)
struct pwrkey_drv_data *pdata = timer_container_of(pdata, t,
check_timer);
struct input_dev *input = pdata->input;
+ bool state_changed = false;
u32 state;
regmap_read(pdata->snvs, SNVS_HPSR_REG, &state);
state = state & SNVS_HPSR_BTN ? 1 : 0;
- /* only report new event if status changed */
- if (state ^ pdata->keystate) {
- pdata->keystate = state;
+ scoped_guard(spinlock_irqsave, &pdata->lock) {
+ /* only report new event if status changed */
+ if (state ^ pdata->keystate) {
+ pdata->keystate = state;
+ state_changed = true;
+ }
+ }
+
+ if (state_changed) {
input_event(input, EV_KEY, pdata->keycode, state);
input_sync(input);
pm_relax(pdata->input->dev.parent);
@@ -74,6 +83,8 @@ static irqreturn_t imx_snvs_pwrkey_interrupt(int irq, void *dev_id)
struct platform_device *pdev = dev_id;
struct pwrkey_drv_data *pdata = platform_get_drvdata(pdev);
struct input_dev *input = pdata->input;
+ bool suspended;
+ int keystate;
u32 lp_status;
pm_wakeup_event(input->dev.parent, 0);
@@ -92,6 +103,21 @@ static irqreturn_t imx_snvs_pwrkey_interrupt(int irq, void *dev_id)
input_sync(input);
pm_relax(input->dev.parent);
} else {
+ /*
+ * Report key press events directly in interrupt handler to prevent event
+ * loss during system suspend.
+ */
+ scoped_guard(spinlock_irqsave, &pdata->lock) {
+ suspended = pdata->suspended;
+ if (suspended) {
+ pdata->keystate = 1;
+ keystate = pdata->keystate;
+ }
+ }
+ if (suspended) {
+ input_report_key(input, pdata->keycode, keystate);
+ input_sync(input);
+ }
mod_timer(&pdata->check_timer,
jiffies + msecs_to_jiffies(DEBOUNCE_TIME));
}
@@ -151,6 +177,7 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
if (pdata->irq < 0)
return pdata->irq;
+ spin_lock_init(&pdata->lock);
error = of_property_read_u32(np, "power-off-time-sec", &val);
if (!error) {
switch (val) {
@@ -219,6 +246,32 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
return 0;
}
+static int __maybe_unused imx_snvs_pwrkey_suspend(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ struct pwrkey_drv_data *pdata = platform_get_drvdata(pdev);
+
+ scoped_guard(spinlock_irqsave, &pdata->lock)
+ pdata->suspended = true;
+
+ return 0;
+}
+
+static int __maybe_unused imx_snvs_pwrkey_resume(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ struct pwrkey_drv_data *pdata = platform_get_drvdata(pdev);
+
+ scoped_guard(spinlock_irqsave, &pdata->lock)
+ pdata->suspended = false;
+
+ return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(imx_snvs_pwrkey_pm_ops,
+ imx_snvs_pwrkey_suspend,
+ imx_snvs_pwrkey_resume);
+
static const struct of_device_id imx_snvs_pwrkey_ids[] = {
{ .compatible = "fsl,sec-v4.0-pwrkey" },
{ /* sentinel */ }
@@ -229,6 +282,7 @@ static struct platform_driver imx_snvs_pwrkey_driver = {
.driver = {
.name = "snvs_pwrkey",
.of_match_table = imx_snvs_pwrkey_ids,
+ .pm = &imx_snvs_pwrkey_pm_ops,
},
.probe = imx_snvs_pwrkey_probe,
};
--
2.34.1
^ permalink raw reply related
* [PATCH v3 3/4] Input: snvs_pwrkey - use local device pointer to simple code
From: joy.zou @ 2026-06-15 7:52 UTC (permalink / raw)
To: Dmitry Torokhov, Frank Li, Bough Chen, Peng Fan, Jacky Bai, Ye Li
Cc: Joy Zou, imx, linux-input, linux-kernel, Joy Zou
In-Reply-To: <20260615-b4-pwrkey-v3-0-9510b1173f6e@oss.nxp.com>
From: Joy Zou <joy.zou@nxp.com>
Use local struct device pointer to avoid reference the platform_device
pointer every time.
No functional change.
Signed-off-by: Joy Zou <joy.zou@nxp.com>
---
Changes for v2:
1. Use dev instead of &pdev->dev for devm_input_allocate_device(),
which was missed in patch v1 per AI review comments.
2. Modify commit message.
---
drivers/input/keyboard/snvs_pwrkey.c | 41 ++++++++++++++++++------------------
1 file changed, 21 insertions(+), 20 deletions(-)
diff --git a/drivers/input/keyboard/snvs_pwrkey.c b/drivers/input/keyboard/snvs_pwrkey.c
index a291812e6d22..4a1d04898482 100644
--- a/drivers/input/keyboard/snvs_pwrkey.c
+++ b/drivers/input/keyboard/snvs_pwrkey.c
@@ -112,6 +112,7 @@ static void imx_snvs_pwrkey_act(void *pdata)
static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
{
+ struct device *dev = &pdev->dev;
struct pwrkey_drv_data *pdata;
struct input_dev *input;
struct device_node *np;
@@ -122,26 +123,26 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
u32 vid;
/* Get SNVS register Page */
- np = pdev->dev.of_node;
+ np = dev->of_node;
if (!np)
- return dev_err_probe(&pdev->dev, -ENODEV, "Device tree node not found\n");
+ return dev_err_probe(dev, -ENODEV, "Device tree node not found\n");
- pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+ pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
if (!pdata)
return -ENOMEM;
pdata->snvs = syscon_regmap_lookup_by_phandle(np, "regmap");
if (IS_ERR(pdata->snvs))
- return dev_err_probe(&pdev->dev, PTR_ERR(pdata->snvs), "Can't get snvs syscon\n");
+ return dev_err_probe(dev, PTR_ERR(pdata->snvs), "Can't get snvs syscon\n");
if (of_property_read_u32(np, "linux,keycode", &pdata->keycode)) {
pdata->keycode = KEY_POWER;
- dev_warn(&pdev->dev, "KEY_POWER without setting in dts\n");
+ dev_warn(dev, "KEY_POWER without setting in dts\n");
}
- clk = devm_clk_get_optional_enabled(&pdev->dev, NULL);
+ clk = devm_clk_get_optional_enabled(dev, NULL);
if (IS_ERR(clk))
- return dev_err_probe(&pdev->dev, PTR_ERR(clk),
+ return dev_err_probe(dev, PTR_ERR(clk),
"Failed to get snvs clock (%pe)\n", clk);
pdata->wakeup = of_property_read_bool(np, "wakeup-source");
@@ -162,7 +163,7 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
bpt = (val / 5) - 1;
break;
default:
- return dev_err_probe(&pdev->dev, -EINVAL,
+ return dev_err_probe(dev, -EINVAL,
"power-off-time-sec %d out of range\n", val);
}
@@ -180,9 +181,9 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
timer_setup(&pdata->check_timer, imx_imx_snvs_check_for_events, 0);
- input = devm_input_allocate_device(&pdev->dev);
+ input = devm_input_allocate_device(dev);
if (!input) {
- dev_err(&pdev->dev, "failed to allocate the input device\n");
+ dev_err(dev, "failed to allocate the input device\n");
return -ENOMEM;
}
@@ -193,27 +194,27 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
input_set_capability(input, EV_KEY, pdata->keycode);
/* input customer action to cancel release timer */
- error = devm_add_action(&pdev->dev, imx_snvs_pwrkey_act, pdata);
+ error = devm_add_action(dev, imx_snvs_pwrkey_act, pdata);
if (error)
- return dev_err_probe(&pdev->dev, error, "failed to register remove action\n");
+ return dev_err_probe(dev, error, "failed to register remove action\n");
pdata->input = input;
platform_set_drvdata(pdev, pdata);
- error = devm_request_irq(&pdev->dev, pdata->irq,
- imx_snvs_pwrkey_interrupt,
- 0, pdev->name, pdev);
+ error = devm_request_irq(dev, pdata->irq,
+ imx_snvs_pwrkey_interrupt,
+ 0, pdev->name, pdev);
if (error)
- return dev_err_probe(&pdev->dev, error, "interrupt not available.\n");
+ return dev_err_probe(dev, error, "interrupt not available.\n");
error = input_register_device(input);
if (error < 0)
- return dev_err_probe(&pdev->dev, error, "failed to register input device\n");
+ return dev_err_probe(dev, error, "failed to register input device\n");
- device_init_wakeup(&pdev->dev, pdata->wakeup);
- error = dev_pm_set_wake_irq(&pdev->dev, pdata->irq);
+ device_init_wakeup(dev, pdata->wakeup);
+ error = dev_pm_set_wake_irq(dev, pdata->irq);
if (error)
- dev_err(&pdev->dev, "irq wake enable failed.\n");
+ dev_err(dev, "irq wake enable failed.\n");
return 0;
}
--
2.34.1
^ permalink raw reply related
* [PATCH v3 2/4] Input: snvs_pwrkey - replace hardcoding -EINVAL with original error code
From: joy.zou @ 2026-06-15 7:52 UTC (permalink / raw)
To: Dmitry Torokhov, Frank Li, Bough Chen, Peng Fan, Jacky Bai, Ye Li
Cc: Joy Zou, imx, linux-input, linux-kernel, Joy Zou
In-Reply-To: <20260615-b4-pwrkey-v3-0-9510b1173f6e@oss.nxp.com>
From: Joy Zou <joy.zou@nxp.com>
Hardcoding -EINVAL discards the actual error code, which breaks probe
deferral (-EPROBE_DEFER) and loses critical diagnostic information
needed for proper kernel error handling.
Signed-off-by: Joy Zou <joy.zou@nxp.com>
---
drivers/input/keyboard/snvs_pwrkey.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/input/keyboard/snvs_pwrkey.c b/drivers/input/keyboard/snvs_pwrkey.c
index 748196fcce75..a291812e6d22 100644
--- a/drivers/input/keyboard/snvs_pwrkey.c
+++ b/drivers/input/keyboard/snvs_pwrkey.c
@@ -148,7 +148,7 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
pdata->irq = platform_get_irq(pdev, 0);
if (pdata->irq < 0)
- return -EINVAL;
+ return pdata->irq;
error = of_property_read_u32(np, "power-off-time-sec", &val);
if (!error) {
--
2.34.1
^ permalink raw reply related
* [PATCH v3 1/4] Input: snvs_pwrkey - make use of dev_err_probe()
From: joy.zou @ 2026-06-15 7:52 UTC (permalink / raw)
To: Dmitry Torokhov, Frank Li, Bough Chen, Peng Fan, Jacky Bai, Ye Li
Cc: Joy Zou, imx, linux-input, linux-kernel, Joy Zou
In-Reply-To: <20260615-b4-pwrkey-v3-0-9510b1173f6e@oss.nxp.com>
From: Joy Zou <joy.zou@nxp.com>
Add dev_err_probe() at return path of probe() to support users to
identify issues easier.
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Joy Zou <joy.zou@nxp.com>
---
Changes in v2:
1. Drop dev_err_probe() change for platform_get_irq() per AI review comments.
2. Add Reviewed-by tag.
---
drivers/input/keyboard/snvs_pwrkey.c | 38 +++++++++++++-----------------------
1 file changed, 14 insertions(+), 24 deletions(-)
diff --git a/drivers/input/keyboard/snvs_pwrkey.c b/drivers/input/keyboard/snvs_pwrkey.c
index 954055aaf6e2..748196fcce75 100644
--- a/drivers/input/keyboard/snvs_pwrkey.c
+++ b/drivers/input/keyboard/snvs_pwrkey.c
@@ -124,17 +124,15 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
/* Get SNVS register Page */
np = pdev->dev.of_node;
if (!np)
- return -ENODEV;
+ return dev_err_probe(&pdev->dev, -ENODEV, "Device tree node not found\n");
pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
if (!pdata)
return -ENOMEM;
pdata->snvs = syscon_regmap_lookup_by_phandle(np, "regmap");
- if (IS_ERR(pdata->snvs)) {
- dev_err(&pdev->dev, "Can't get snvs syscon\n");
- return PTR_ERR(pdata->snvs);
- }
+ if (IS_ERR(pdata->snvs))
+ return dev_err_probe(&pdev->dev, PTR_ERR(pdata->snvs), "Can't get snvs syscon\n");
if (of_property_read_u32(np, "linux,keycode", &pdata->keycode)) {
pdata->keycode = KEY_POWER;
@@ -142,10 +140,9 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
}
clk = devm_clk_get_optional_enabled(&pdev->dev, NULL);
- if (IS_ERR(clk)) {
- dev_err(&pdev->dev, "Failed to get snvs clock (%pe)\n", clk);
- return PTR_ERR(clk);
- }
+ if (IS_ERR(clk))
+ return dev_err_probe(&pdev->dev, PTR_ERR(clk),
+ "Failed to get snvs clock (%pe)\n", clk);
pdata->wakeup = of_property_read_bool(np, "wakeup-source");
@@ -165,9 +162,8 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
bpt = (val / 5) - 1;
break;
default:
- dev_err(&pdev->dev,
- "power-off-time-sec %d out of range\n", val);
- return -EINVAL;
+ return dev_err_probe(&pdev->dev, -EINVAL,
+ "power-off-time-sec %d out of range\n", val);
}
regmap_update_bits(pdata->snvs, SNVS_LPCR_REG, SNVS_LPCR_BPT_MASK,
@@ -198,10 +194,8 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
/* input customer action to cancel release timer */
error = devm_add_action(&pdev->dev, imx_snvs_pwrkey_act, pdata);
- if (error) {
- dev_err(&pdev->dev, "failed to register remove action\n");
- return error;
- }
+ if (error)
+ return dev_err_probe(&pdev->dev, error, "failed to register remove action\n");
pdata->input = input;
platform_set_drvdata(pdev, pdata);
@@ -209,16 +203,12 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
error = devm_request_irq(&pdev->dev, pdata->irq,
imx_snvs_pwrkey_interrupt,
0, pdev->name, pdev);
- if (error) {
- dev_err(&pdev->dev, "interrupt not available.\n");
- return error;
- }
+ if (error)
+ return dev_err_probe(&pdev->dev, error, "interrupt not available.\n");
error = input_register_device(input);
- if (error < 0) {
- dev_err(&pdev->dev, "failed to register input device\n");
- return error;
- }
+ if (error < 0)
+ return dev_err_probe(&pdev->dev, error, "failed to register input device\n");
device_init_wakeup(&pdev->dev, pdata->wakeup);
error = dev_pm_set_wake_irq(&pdev->dev, pdata->irq);
--
2.34.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox