[PATCH v5 0/6] Input: imx6ul_tsc - set glitch threshold by dts property

[PATCH v5 0/6] Input: imx6ul_tsc - set glitch threshold by dts property

[Dario Binacchi]

The series allows setting the glitch threshold for the detected signal
from a DTS property instead of a hardcoded value.
In addition, I applied a patch that replaces opencoded masking and
shifting, with BIT(), GENMASK(), FIELD_GET() and FIELD_PREP() macros.

I didn’t remove patches:
 - 2/6 Input: imx6ul_tsc - use BIT, FIELD_{GET,PREP} and GENMASK macros
 - 1/6 Input: imx6ul_tsc - fix typo in register name
even though they were accepted, to avoid generating conflicts detected
by the kernel test robot.

Changes in v5:
- I didn’t remove patches:
   - 2/6 Input: imx6ul_tsc - use BIT, FIELD_{GET,PREP} and GENMASK macros
   - 1/6 Input: imx6ul_tsc - fix typo in register name
  even though they were accepted, to avoid generating conflicts detected
  by the kernel test robot.

Changes in v4:
- Adjust property description fsl,imx6ul-tsc.yaml following the
  suggestions of Conor Dooley and Frank Li.

Changes in v3:
- Remove the final part of the description that refers to
  implementation details in fsl,imx6ul-tsc.yaml.

Changes in v2:
- Replace patch ("dt-bindings: input: touchscreen: fsl,imx6ul-tsc: add
  fsl,glitch-threshold") with ("dt-bindings: touchscreen: add
  touchscreen-glitch-threshold-ns property"), making the previous property
  general by moving it to touchscreen.yaml.
- Rework "Input: imx6ul_tsc - set glitch threshold by DTS property" patch
  to match changes made to the DTS property.
- Move "Input: imx6ul_tsc - use BIT, FIELD_{GET,PREP} and GENMASK macros"
  patch right after the patch fixing the typo.

Dario Binacchi (5):
  Input: imx6ul_tsc - use BIT, FIELD_{GET,PREP} and GENMASK macros
  dt-bindings: touchscreen: add touchscreen-glitch-threshold-ns property
  dt-bindings: touchscreen: fsl,imx6ul-tsc: support glitch thresold
  ARM: dts: imx6ull-engicam-microgea-bmm: set touchscreen glitch
    threshold
  Input: imx6ul_tsc - set glitch threshold by DTS property

Michael Trimarchi (1):
  Input: imx6ul_tsc - fix typo in register name

 .../input/touchscreen/fsl,imx6ul-tsc.yaml     |  14 ++
 .../input/touchscreen/touchscreen.yaml        |   4 +
 .../nxp/imx/imx6ull-engicam-microgea-bmm.dts  |   1 +
 drivers/input/touchscreen/imx6ul_tsc.c        | 122 +++++++++++-------
 4 files changed, 97 insertions(+), 44 deletions(-)

-- 
2.43.0

base-commit: 8b789f2b7602a818e7c7488c74414fae21392b63
branch: tsc_de_glitch

[PATCH v5 1/6] Input: imx6ul_tsc - fix typo in register name

[Dario Binacchi]

From: Michael Trimarchi <michael@amarulasolutions.com>

Replace 'SETING' with 'SETTING'.

Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>

---

(no changes since v2)

Changes in v2:
- Add Reviewed-by tag of Frank Li.

 drivers/input/touchscreen/imx6ul_tsc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/touchscreen/imx6ul_tsc.c b/drivers/input/touchscreen/imx6ul_tsc.c
index 6ac8fa84ed9f..c2c6e50efc54 100644
--- a/drivers/input/touchscreen/imx6ul_tsc.c
+++ b/drivers/input/touchscreen/imx6ul_tsc.c
@@ -55,7 +55,7 @@
 #define ADC_TIMEOUT		msecs_to_jiffies(100)
 
 /* TSC registers */
-#define REG_TSC_BASIC_SETING	0x00
+#define REG_TSC_BASIC_SETTING	0x00
 #define REG_TSC_PRE_CHARGE_TIME	0x10
 #define REG_TSC_FLOW_CONTROL	0x20
 #define REG_TSC_MEASURE_VALUE	0x30
@@ -192,7 +192,7 @@ static void imx6ul_tsc_set(struct imx6ul_tsc *tsc)
 
 	basic_setting |= tsc->measure_delay_time << 8;
 	basic_setting |= DETECT_4_WIRE_MODE | AUTO_MEASURE;
-	writel(basic_setting, tsc->tsc_regs + REG_TSC_BASIC_SETING);
+	writel(basic_setting, tsc->tsc_regs + REG_TSC_BASIC_SETTING);
 
 	writel(DE_GLITCH_2, tsc->tsc_regs + REG_TSC_DEBUG_MODE2);
 
-- 
2.43.0

[PATCH v5 2/6] Input: imx6ul_tsc - use BIT, FIELD_{GET,PREP} and GENMASK macros

[Dario Binacchi]

Replace opencoded masking and shifting, with BIT(), GENMASK(),
FIELD_GET() and FIELD_PREP() macros.

Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>

---

(no changes since v2)

Changes in v2:
- Add Reviewed-by tag of Frank Li.
- Move the patch right after the one fixing the typo according
  to Frank Li's suggestions.

 drivers/input/touchscreen/imx6ul_tsc.c | 96 +++++++++++++++-----------
 1 file changed, 54 insertions(+), 42 deletions(-)

diff --git a/drivers/input/touchscreen/imx6ul_tsc.c b/drivers/input/touchscreen/imx6ul_tsc.c
index c2c6e50efc54..e2c59cc7c82c 100644
--- a/drivers/input/touchscreen/imx6ul_tsc.c
+++ b/drivers/input/touchscreen/imx6ul_tsc.c
@@ -7,6 +7,7 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/bitfield.h>
 #include <linux/gpio/consumer.h>
 #include <linux/input.h>
 #include <linux/slab.h>
@@ -20,25 +21,23 @@
 #include <linux/log2.h>
 
 /* ADC configuration registers field define */
-#define ADC_AIEN		(0x1 << 7)
+#define ADC_AIEN		BIT(7)
+#define ADC_ADCH_MASK		GENMASK(4, 0)
 #define ADC_CONV_DISABLE	0x1F
-#define ADC_AVGE		(0x1 << 5)
-#define ADC_CAL			(0x1 << 7)
-#define ADC_CALF		0x2
-#define ADC_12BIT_MODE		(0x2 << 2)
-#define ADC_CONV_MODE_MASK	(0x3 << 2)
+#define ADC_AVGE		BIT(5)
+#define ADC_CAL			BIT(7)
+#define ADC_CALF		BIT(1)
+#define ADC_CONV_MODE_MASK	GENMASK(3, 2)
+#define ADC_12BIT_MODE		0x2
 #define ADC_IPG_CLK		0x00
-#define ADC_INPUT_CLK_MASK	0x3
-#define ADC_CLK_DIV_8		(0x03 << 5)
-#define ADC_CLK_DIV_MASK	(0x3 << 5)
-#define ADC_SHORT_SAMPLE_MODE	(0x0 << 4)
-#define ADC_SAMPLE_MODE_MASK	(0x1 << 4)
-#define ADC_HARDWARE_TRIGGER	(0x1 << 13)
-#define ADC_AVGS_SHIFT		14
-#define ADC_AVGS_MASK		(0x3 << 14)
+#define ADC_INPUT_CLK_MASK	GENMASK(1, 0)
+#define ADC_CLK_DIV_8		0x03
+#define ADC_CLK_DIV_MASK	GENMASK(6, 5)
+#define ADC_SAMPLE_MODE		BIT(4)
+#define ADC_HARDWARE_TRIGGER	BIT(13)
+#define ADC_AVGS_MASK		GENMASK(15, 14)
 #define SELECT_CHANNEL_4	0x04
 #define SELECT_CHANNEL_1	0x01
-#define DISABLE_CONVERSION_INT	(0x0 << 7)
 
 /* ADC registers */
 #define REG_ADC_HC0		0x00
@@ -65,19 +64,26 @@
 #define REG_TSC_DEBUG_MODE	0x70
 #define REG_TSC_DEBUG_MODE2	0x80
 
+/* TSC_MEASURE_VALUE register field define */
+#define X_VALUE_MASK		GENMASK(27, 16)
+#define Y_VALUE_MASK		GENMASK(11, 0)
+
 /* TSC configuration registers field define */
-#define DETECT_4_WIRE_MODE	(0x0 << 4)
-#define AUTO_MEASURE		0x1
-#define MEASURE_SIGNAL		0x1
-#define DETECT_SIGNAL		(0x1 << 4)
-#define VALID_SIGNAL		(0x1 << 8)
-#define MEASURE_INT_EN		0x1
-#define MEASURE_SIG_EN		0x1
-#define VALID_SIG_EN		(0x1 << 8)
-#define DE_GLITCH_2		(0x2 << 29)
-#define START_SENSE		(0x1 << 12)
-#define TSC_DISABLE		(0x1 << 16)
+#define MEASURE_DELAY_TIME_MASK	GENMASK(31, 8)
+#define DETECT_5_WIRE_MODE	BIT(4)
+#define AUTO_MEASURE		BIT(0)
+#define MEASURE_SIGNAL		BIT(0)
+#define DETECT_SIGNAL		BIT(4)
+#define VALID_SIGNAL		BIT(8)
+#define MEASURE_INT_EN		BIT(0)
+#define MEASURE_SIG_EN		BIT(0)
+#define VALID_SIG_EN		BIT(8)
+#define DE_GLITCH_MASK		GENMASK(30, 29)
+#define DE_GLITCH_2		0x02
+#define START_SENSE		BIT(12)
+#define TSC_DISABLE		BIT(16)
 #define DETECT_MODE		0x2
+#define STATE_MACHINE_MASK	GENMASK(22, 20)
 
 struct imx6ul_tsc {
 	struct device *dev;
@@ -112,19 +118,20 @@ static int imx6ul_adc_init(struct imx6ul_tsc *tsc)
 
 	adc_cfg = readl(tsc->adc_regs + REG_ADC_CFG);
 	adc_cfg &= ~(ADC_CONV_MODE_MASK | ADC_INPUT_CLK_MASK);
-	adc_cfg |= ADC_12BIT_MODE | ADC_IPG_CLK;
-	adc_cfg &= ~(ADC_CLK_DIV_MASK | ADC_SAMPLE_MODE_MASK);
-	adc_cfg |= ADC_CLK_DIV_8 | ADC_SHORT_SAMPLE_MODE;
+	adc_cfg |= FIELD_PREP(ADC_CONV_MODE_MASK, ADC_12BIT_MODE) |
+		FIELD_PREP(ADC_INPUT_CLK_MASK, ADC_IPG_CLK);
+	adc_cfg &= ~(ADC_CLK_DIV_MASK | ADC_SAMPLE_MODE);
+	adc_cfg |= FIELD_PREP(ADC_CLK_DIV_MASK, ADC_CLK_DIV_8);
 	if (tsc->average_enable) {
 		adc_cfg &= ~ADC_AVGS_MASK;
-		adc_cfg |= (tsc->average_select) << ADC_AVGS_SHIFT;
+		adc_cfg |= FIELD_PREP(ADC_AVGS_MASK, tsc->average_select);
 	}
 	adc_cfg &= ~ADC_HARDWARE_TRIGGER;
 	writel(adc_cfg, tsc->adc_regs + REG_ADC_CFG);
 
 	/* enable calibration interrupt */
 	adc_hc |= ADC_AIEN;
-	adc_hc |= ADC_CONV_DISABLE;
+	adc_hc |= FIELD_PREP(ADC_ADCH_MASK, ADC_CONV_DISABLE);
 	writel(adc_hc, tsc->adc_regs + REG_ADC_HC0);
 
 	/* start ADC calibration */
@@ -164,19 +171,21 @@ static void imx6ul_tsc_channel_config(struct imx6ul_tsc *tsc)
 {
 	u32 adc_hc0, adc_hc1, adc_hc2, adc_hc3, adc_hc4;
 
-	adc_hc0 = DISABLE_CONVERSION_INT;
+	adc_hc0 = FIELD_PREP(ADC_AIEN, 0);
 	writel(adc_hc0, tsc->adc_regs + REG_ADC_HC0);
 
-	adc_hc1 = DISABLE_CONVERSION_INT | SELECT_CHANNEL_4;
+	adc_hc1 = FIELD_PREP(ADC_AIEN, 0) |
+		FIELD_PREP(ADC_ADCH_MASK, SELECT_CHANNEL_4);
 	writel(adc_hc1, tsc->adc_regs + REG_ADC_HC1);
 
-	adc_hc2 = DISABLE_CONVERSION_INT;
+	adc_hc2 = FIELD_PREP(ADC_AIEN, 0);
 	writel(adc_hc2, tsc->adc_regs + REG_ADC_HC2);
 
-	adc_hc3 = DISABLE_CONVERSION_INT | SELECT_CHANNEL_1;
+	adc_hc3 = FIELD_PREP(ADC_AIEN, 0) |
+		FIELD_PREP(ADC_ADCH_MASK, SELECT_CHANNEL_1);
 	writel(adc_hc3, tsc->adc_regs + REG_ADC_HC3);
 
-	adc_hc4 = DISABLE_CONVERSION_INT;
+	adc_hc4 = FIELD_PREP(ADC_AIEN, 0);
 	writel(adc_hc4, tsc->adc_regs + REG_ADC_HC4);
 }
 
@@ -188,13 +197,16 @@ static void imx6ul_tsc_channel_config(struct imx6ul_tsc *tsc)
 static void imx6ul_tsc_set(struct imx6ul_tsc *tsc)
 {
 	u32 basic_setting = 0;
+	u32 debug_mode2;
 	u32 start;
 
-	basic_setting |= tsc->measure_delay_time << 8;
-	basic_setting |= DETECT_4_WIRE_MODE | AUTO_MEASURE;
+	basic_setting |= FIELD_PREP(MEASURE_DELAY_TIME_MASK,
+				    tsc->measure_delay_time);
+	basic_setting |= AUTO_MEASURE;
 	writel(basic_setting, tsc->tsc_regs + REG_TSC_BASIC_SETTING);
 
-	writel(DE_GLITCH_2, tsc->tsc_regs + REG_TSC_DEBUG_MODE2);
+	debug_mode2 = FIELD_PREP(DE_GLITCH_MASK, DE_GLITCH_2);
+	writel(debug_mode2, tsc->tsc_regs + REG_TSC_DEBUG_MODE2);
 
 	writel(tsc->pre_charge_time, tsc->tsc_regs + REG_TSC_PRE_CHARGE_TIME);
 	writel(MEASURE_INT_EN, tsc->tsc_regs + REG_TSC_INT_EN);
@@ -250,7 +262,7 @@ static bool tsc_wait_detect_mode(struct imx6ul_tsc *tsc)
 
 		usleep_range(200, 400);
 		debug_mode2 = readl(tsc->tsc_regs + REG_TSC_DEBUG_MODE2);
-		state_machine = (debug_mode2 >> 20) & 0x7;
+		state_machine = FIELD_GET(STATE_MACHINE_MASK, debug_mode2);
 	} while (state_machine != DETECT_MODE);
 
 	usleep_range(200, 400);
@@ -278,8 +290,8 @@ static irqreturn_t tsc_irq_fn(int irq, void *dev_id)
 
 	if (status & MEASURE_SIGNAL) {
 		value = readl(tsc->tsc_regs + REG_TSC_MEASURE_VALUE);
-		x = (value >> 16) & 0x0fff;
-		y = value & 0x0fff;
+		x = FIELD_GET(X_VALUE_MASK, value);
+		y = FIELD_GET(Y_VALUE_MASK, value);
 
 		/*
 		 * In detect mode, we can get the xnur gpio value,
-- 
2.43.0

[PATCH v5 3/6] dt-bindings: touchscreen: add touchscreen-glitch-threshold-ns property

[Dario Binacchi]

Add support for glitch threshold configuration. A detected signal is valid
only if it lasts longer than the set threshold; otherwise, it is regarded
as a glitch.

Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>

---

Changes in v5:
- Add Acked-by tag of Conor Dooley

Changes in v2:
- Added in v2.

 .../devicetree/bindings/input/touchscreen/touchscreen.yaml    | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
index 3e3572aa483a..a60b4d08620d 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
+++ b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
@@ -206,6 +206,10 @@ properties:
 
         unevaluatedProperties: false
 
+  touchscreen-glitch-threshold-ns:
+    description: Minimum duration in nanoseconds a signal must remain stable
+      to be considered valid.
+
 dependencies:
   touchscreen-size-x: [ touchscreen-size-y ]
   touchscreen-size-y: [ touchscreen-size-x ]
-- 
2.43.0

[PATCH v5 4/6] dt-bindings: touchscreen: fsl,imx6ul-tsc: support glitch thresold

[Dario Binacchi]

Support the touchscreen-glitch-threshold-ns property.

Drivers must convert this value to IPG clock cycles and map it to one of
the four discrete thresholds exposed by the TSC_DEBUG_MODE2 register:

  0: 8191 IPG cycles
  1: 4095 IPG cycles
  2: 2047 IPG cycles
  3: 1023 IPG cycles

Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com>

---

(no changes since v4)

Changes in v4:
- Adjust property description following the suggestions of
  Conor Dooley and Frank Li.
- Update the commit description.

Changes in v3:
- Remove the final part of the description that refers to
  implementation details.

 .../bindings/input/touchscreen/fsl,imx6ul-tsc.yaml | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/Documentation/devicetree/bindings/input/touchscreen/fsl,imx6ul-tsc.yaml b/Documentation/devicetree/bindings/input/touchscreen/fsl,imx6ul-tsc.yaml
index 678756ad0f92..1975f741cf3d 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/fsl,imx6ul-tsc.yaml
+++ b/Documentation/devicetree/bindings/input/touchscreen/fsl,imx6ul-tsc.yaml
@@ -62,6 +62,20 @@ properties:
     description: Number of data samples which are averaged for each read.
     enum: [ 1, 4, 8, 16, 32 ]
 
+  touchscreen-glitch-threshold-ns:
+    description: |
+      Minimum duration in nanoseconds a signal must remain stable
+      to be considered valid.
+
+      Drivers must convert this value to IPG clock cycles and map
+      it to one of the four discrete thresholds exposed by the
+      TSC_DEBUG_MODE2 register:
+
+        0: 8191 IPG cycles
+        1: 4095 IPG cycles
+        2: 2047 IPG cycles
+        3: 1023 IPG cycles
+
 required:
   - compatible
   - reg
-- 
2.43.0

[PATCH v5 6/6] Input: imx6ul_tsc - set glitch threshold by DTS property

[Dario Binacchi]

Set the glitch threshold by DTS property and keep the existing default
behavior if the 'touchscreen-glitch-threshold-ns' is not present.

Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>

---

Changes in v5:
- I didn’t remove patches:
   - 2/6 Input: imx6ul_tsc - use BIT, FIELD_{GET,PREP} and GENMASK macros
   - 1/6 Input: imx6ul_tsc - fix typo in register name
  even though they were accepted, to avoid generating conflicts detected
  by the kernel test robot.
- Re-work the commit message
- Add Reviewed-by tag of Frank Li

Changes in v4:
- Adjust property description fsl,imx6ul-tsc.yaml following the
  suggestions of Conor Dooley and Frank Li.

Changes in v3:
- Remove the final part of the description that refers to
  implementation details in fsl,imx6ul-tsc.yaml.

Changes in v2:
- Replace patch ("dt-bindings: input: touchscreen: fsl,imx6ul-tsc: add
  fsl,glitch-threshold") with ("dt-bindings: touchscreen: add
  touchscreen-glitch-threshold-ns property"), making the previous property
  general by moving it to touchscreen.yaml.
- Rework "Input: imx6ul_tsc - set glitch threshold by DTS property" patch
  to match changes made to the DTS property.
- Move "Input: imx6ul_tsc - use BIT, FIELD_{GET,PREP} and GENMASK macros"
  patch right after the patch fixing the typo.
- Rework to match changes made to the DTS property.

 drivers/input/touchscreen/imx6ul_tsc.c | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/input/touchscreen/imx6ul_tsc.c b/drivers/input/touchscreen/imx6ul_tsc.c
index e2c59cc7c82c..0d753aa05fbf 100644
--- a/drivers/input/touchscreen/imx6ul_tsc.c
+++ b/drivers/input/touchscreen/imx6ul_tsc.c
@@ -79,7 +79,7 @@
 #define MEASURE_SIG_EN		BIT(0)
 #define VALID_SIG_EN		BIT(8)
 #define DE_GLITCH_MASK		GENMASK(30, 29)
-#define DE_GLITCH_2		0x02
+#define DE_GLITCH_DEF		0x02
 #define START_SENSE		BIT(12)
 #define TSC_DISABLE		BIT(16)
 #define DETECT_MODE		0x2
@@ -98,6 +98,7 @@ struct imx6ul_tsc {
 	u32 pre_charge_time;
 	bool average_enable;
 	u32 average_select;
+	u32 de_glitch;
 
 	struct completion completion;
 };
@@ -205,7 +206,7 @@ static void imx6ul_tsc_set(struct imx6ul_tsc *tsc)
 	basic_setting |= AUTO_MEASURE;
 	writel(basic_setting, tsc->tsc_regs + REG_TSC_BASIC_SETTING);
 
-	debug_mode2 = FIELD_PREP(DE_GLITCH_MASK, DE_GLITCH_2);
+	debug_mode2 = FIELD_PREP(DE_GLITCH_MASK, tsc->de_glitch);
 	writel(debug_mode2, tsc->tsc_regs + REG_TSC_DEBUG_MODE2);
 
 	writel(tsc->pre_charge_time, tsc->tsc_regs + REG_TSC_PRE_CHARGE_TIME);
@@ -391,6 +392,7 @@ static int imx6ul_tsc_probe(struct platform_device *pdev)
 	int tsc_irq;
 	int adc_irq;
 	u32 average_samples;
+	u32 de_glitch;
 
 	tsc = devm_kzalloc(&pdev->dev, sizeof(*tsc), GFP_KERNEL);
 	if (!tsc)
@@ -513,6 +515,26 @@ static int imx6ul_tsc_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	err = of_property_read_u32(np, "touchscreen-glitch-threshold-ns",
+				   &de_glitch);
+	if (err) {
+		tsc->de_glitch = DE_GLITCH_DEF;
+	} else {
+		u64 cycles;
+		unsigned long rate = clk_get_rate(tsc->tsc_clk);
+
+		cycles = DIV64_U64_ROUND_UP((u64)de_glitch * rate, NSEC_PER_SEC);
+
+		if (cycles <= 0x3ff)
+			tsc->de_glitch = 3;
+		else if (cycles <= 0x7ff)
+			tsc->de_glitch = 2;
+		else if (cycles <= 0xfff)
+			tsc->de_glitch = 1;
+		else
+			tsc->de_glitch = 0;
+	}
+
 	err = input_register_device(tsc->input);
 	if (err) {
 		dev_err(&pdev->dev,
-- 
2.43.0

Re: [PATCH v5 3/6] dt-bindings: touchscreen: add touchscreen-glitch-threshold-ns property

[Rob Herring]

On Thu, Sep 18, 2025 at 05:52:31PM +0200, Dario Binacchi wrote:
> Add support for glitch threshold configuration. A detected signal is valid
> only if it lasts longer than the set threshold; otherwise, it is regarded
> as a glitch.
> 
> Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com>
> Acked-by: Conor Dooley <conor.dooley@microchip.com>
> 
> ---
> 
> Changes in v5:
> - Add Acked-by tag of Conor Dooley
> 
> Changes in v2:
> - Added in v2.
> 
>  .../devicetree/bindings/input/touchscreen/touchscreen.yaml    | 4 ++++
>  1 file changed, 4 insertions(+)
> 
> diff --git a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> index 3e3572aa483a..a60b4d08620d 100644
> --- a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> +++ b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> @@ -206,6 +206,10 @@ properties:
>  
>          unevaluatedProperties: false
>  
> +  touchscreen-glitch-threshold-ns:
> +    description: Minimum duration in nanoseconds a signal must remain stable
> +      to be considered valid.

What's wrong with debounce-delay-ms?

Re: [PATCH v5 3/6] dt-bindings: touchscreen: add touchscreen-glitch-threshold-ns property

[Dario Binacchi]

On Thu, Sep 18, 2025 at 10:04 PM Rob Herring <robh@kernel.org> wrote:
>
> On Thu, Sep 18, 2025 at 05:52:31PM +0200, Dario Binacchi wrote:
> > Add support for glitch threshold configuration. A detected signal is valid
> > only if it lasts longer than the set threshold; otherwise, it is regarded
> > as a glitch.
> >
> > Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com>
> > Acked-by: Conor Dooley <conor.dooley@microchip.com>
> >
> > ---
> >
> > Changes in v5:
> > - Add Acked-by tag of Conor Dooley
> >
> > Changes in v2:
> > - Added in v2.
> >
> >  .../devicetree/bindings/input/touchscreen/touchscreen.yaml    | 4 ++++
> >  1 file changed, 4 insertions(+)
> >
> > diff --git a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > index 3e3572aa483a..a60b4d08620d 100644
> > --- a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > +++ b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > @@ -206,6 +206,10 @@ properties:
> >
> >          unevaluatedProperties: false
> >
> > +  touchscreen-glitch-threshold-ns:
> > +    description: Minimum duration in nanoseconds a signal must remain stable
> > +      to be considered valid.
>
> What's wrong with debounce-delay-ms?

Do you mean that I should rename touchscreen-glitch-threshold-ns to
debounce-delay-ms?

Thanks and regards,
Dario

-- 

Dario Binacchi

Senior Embedded Linux Developer

dario.binacchi@amarulasolutions.com

__________________________________


Amarula Solutions SRL

Via Le Canevare 30, 31100 Treviso, Veneto, IT

T. +39 042 243 5310
info@amarulasolutions.com

www.amarulasolutions.com

Re: [PATCH v5 3/6] dt-bindings: touchscreen: add touchscreen-glitch-threshold-ns property

[Rob Herring]

On Thu, Sep 18, 2025 at 10:37:37PM +0200, Dario Binacchi wrote:
> On Thu, Sep 18, 2025 at 10:04 PM Rob Herring <robh@kernel.org> wrote:
> >
> > On Thu, Sep 18, 2025 at 05:52:31PM +0200, Dario Binacchi wrote:
> > > Add support for glitch threshold configuration. A detected signal is valid
> > > only if it lasts longer than the set threshold; otherwise, it is regarded
> > > as a glitch.
> > >
> > > Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com>
> > > Acked-by: Conor Dooley <conor.dooley@microchip.com>
> > >
> > > ---
> > >
> > > Changes in v5:
> > > - Add Acked-by tag of Conor Dooley
> > >
> > > Changes in v2:
> > > - Added in v2.
> > >
> > >  .../devicetree/bindings/input/touchscreen/touchscreen.yaml    | 4 ++++
> > >  1 file changed, 4 insertions(+)
> > >
> > > diff --git a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > index 3e3572aa483a..a60b4d08620d 100644
> > > --- a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > +++ b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > @@ -206,6 +206,10 @@ properties:
> > >
> > >          unevaluatedProperties: false
> > >
> > > +  touchscreen-glitch-threshold-ns:
> > > +    description: Minimum duration in nanoseconds a signal must remain stable
> > > +      to be considered valid.
> >
> > What's wrong with debounce-delay-ms?
> 
> Do you mean that I should rename touchscreen-glitch-threshold-ns to
> debounce-delay-ms?

I mean that's the common property we already have, so use it or explain 
why you aren't using it. I suppose the definition is technically a bit 
different if it's purely a s/w delay vs. h/w monitoring of the signal 
state. I don't think it matters if the interpretation by each driver is 
a bit different.

Maybe msec is not enough resolution for you could be another reason? 
Looks like your h/w supports that assuming the clock frequency is 10s 
of MHz. But are touchscreen glitches really in sub msec times? Not in my 
experience, but that's 20 years ago on resistive touchscreens...

Rob

Re: [PATCH v5 3/6] dt-bindings: touchscreen: add touchscreen-glitch-threshold-ns property

[Dario Binacchi]

On Fri, Sep 19, 2025 at 4:38 PM Rob Herring <robh@kernel.org> wrote:
>
> On Thu, Sep 18, 2025 at 10:37:37PM +0200, Dario Binacchi wrote:
> > On Thu, Sep 18, 2025 at 10:04 PM Rob Herring <robh@kernel.org> wrote:
> > >
> > > On Thu, Sep 18, 2025 at 05:52:31PM +0200, Dario Binacchi wrote:
> > > > Add support for glitch threshold configuration. A detected signal is valid
> > > > only if it lasts longer than the set threshold; otherwise, it is regarded
> > > > as a glitch.
> > > >
> > > > Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com>
> > > > Acked-by: Conor Dooley <conor.dooley@microchip.com>
> > > >
> > > > ---
> > > >
> > > > Changes in v5:
> > > > - Add Acked-by tag of Conor Dooley
> > > >
> > > > Changes in v2:
> > > > - Added in v2.
> > > >
> > > >  .../devicetree/bindings/input/touchscreen/touchscreen.yaml    | 4 ++++
> > > >  1 file changed, 4 insertions(+)
> > > >
> > > > diff --git a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > > index 3e3572aa483a..a60b4d08620d 100644
> > > > --- a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > > +++ b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > > @@ -206,6 +206,10 @@ properties:
> > > >
> > > >          unevaluatedProperties: false
> > > >
> > > > +  touchscreen-glitch-threshold-ns:
> > > > +    description: Minimum duration in nanoseconds a signal must remain stable
> > > > +      to be considered valid.
> > >
> > > What's wrong with debounce-delay-ms?
> >
> > Do you mean that I should rename touchscreen-glitch-threshold-ns to
> > debounce-delay-ms?
>
> I mean that's the common property we already have, so use it or explain
> why you aren't using it. I suppose the definition is technically a bit
> different if it's purely a s/w delay vs. h/w monitoring of the signal
> state. I don't think it matters if the interpretation by each driver is
> a bit different.
>
> Maybe msec is not enough resolution for you could be another reason?

Yes, this is the main reason. As specified in the following patch:
  v5 4/6 dt-bindings: touchscreen: fsl,imx6ul-tsc: support glitch threshold

Drivers must convert this value to IPG clock cycles and map
it to one of the four discrete thresholds exposed by the
TSC_DEBUG_MODE2 register:

  0: 8191 IPG cycles
  1: 4095 IPG cycles
  2: 2047 IPG cycles
  3: 1023 IPG cycles

In my case, the IPG clock runs at 66 MHz, which corresponds to:

124 µs for 0
62 µs for 1
31 us for 2
15 us for 3

So using milliseconds would not fit my use case. A possible trade-off
could be to use debounce-delay-us. Would that be acceptable?

Thanks and regards
Dario

> Looks like your h/w supports that assuming the clock frequency is 10s
> of MHz. But are touchscreen glitches really in sub msec times? Not in my
> experience, but that's 20 years ago on resistive touchscreens...
>
> Rob



-- 

Dario Binacchi

Senior Embedded Linux Developer

dario.binacchi@amarulasolutions.com

__________________________________


Amarula Solutions SRL

Via Le Canevare 30, 31100 Treviso, Veneto, IT

T. +39 042 243 5310
info@amarulasolutions.com

www.amarulasolutions.com

Re: [PATCH v5 3/6] dt-bindings: touchscreen: add touchscreen-glitch-threshold-ns property

[Rob Herring]

On Fri, Sep 19, 2025 at 05:12:42PM +0200, Dario Binacchi wrote:
> On Fri, Sep 19, 2025 at 4:38 PM Rob Herring <robh@kernel.org> wrote:
> >
> > On Thu, Sep 18, 2025 at 10:37:37PM +0200, Dario Binacchi wrote:
> > > On Thu, Sep 18, 2025 at 10:04 PM Rob Herring <robh@kernel.org> wrote:
> > > >
> > > > On Thu, Sep 18, 2025 at 05:52:31PM +0200, Dario Binacchi wrote:
> > > > > Add support for glitch threshold configuration. A detected signal is valid
> > > > > only if it lasts longer than the set threshold; otherwise, it is regarded
> > > > > as a glitch.
> > > > >
> > > > > Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com>
> > > > > Acked-by: Conor Dooley <conor.dooley@microchip.com>
> > > > >
> > > > > ---
> > > > >
> > > > > Changes in v5:
> > > > > - Add Acked-by tag of Conor Dooley
> > > > >
> > > > > Changes in v2:
> > > > > - Added in v2.
> > > > >
> > > > >  .../devicetree/bindings/input/touchscreen/touchscreen.yaml    | 4 ++++
> > > > >  1 file changed, 4 insertions(+)
> > > > >
> > > > > diff --git a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > > > index 3e3572aa483a..a60b4d08620d 100644
> > > > > --- a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > > > +++ b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > > > @@ -206,6 +206,10 @@ properties:
> > > > >
> > > > >          unevaluatedProperties: false
> > > > >
> > > > > +  touchscreen-glitch-threshold-ns:
> > > > > +    description: Minimum duration in nanoseconds a signal must remain stable
> > > > > +      to be considered valid.
> > > >
> > > > What's wrong with debounce-delay-ms?
> > >
> > > Do you mean that I should rename touchscreen-glitch-threshold-ns to
> > > debounce-delay-ms?
> >
> > I mean that's the common property we already have, so use it or explain
> > why you aren't using it. I suppose the definition is technically a bit
> > different if it's purely a s/w delay vs. h/w monitoring of the signal
> > state. I don't think it matters if the interpretation by each driver is
> > a bit different.
> >
> > Maybe msec is not enough resolution for you could be another reason?
> 
> Yes, this is the main reason. As specified in the following patch:
>   v5 4/6 dt-bindings: touchscreen: fsl,imx6ul-tsc: support glitch threshold
> 
> Drivers must convert this value to IPG clock cycles and map
> it to one of the four discrete thresholds exposed by the
> TSC_DEBUG_MODE2 register:
> 
>   0: 8191 IPG cycles
>   1: 4095 IPG cycles
>   2: 2047 IPG cycles
>   3: 1023 IPG cycles
> 
> In my case, the IPG clock runs at 66 MHz, which corresponds to:
> 
> 124 µs for 0
> 62 µs for 1
> 31 us for 2
> 15 us for 3
> 
> So using milliseconds would not fit my use case. A possible trade-off
> could be to use debounce-delay-us. Would that be acceptable?

I agree it wouldn't map to what the h/w provides, but is what the h/w 
provides actually useful? There's plenty of h/w designed that's not 
useful. 15us is quite short for a glitch. Do you have an actual cases 
where the different values above are needed?

Rob

Re: [PATCH v5 3/6] dt-bindings: touchscreen: add touchscreen-glitch-threshold-ns property

[Dario Binacchi]

On Fri, Sep 19, 2025 at 10:44 PM Rob Herring <robh@kernel.org> wrote:
>
> On Fri, Sep 19, 2025 at 05:12:42PM +0200, Dario Binacchi wrote:
> > On Fri, Sep 19, 2025 at 4:38 PM Rob Herring <robh@kernel.org> wrote:
> > >
> > > On Thu, Sep 18, 2025 at 10:37:37PM +0200, Dario Binacchi wrote:
> > > > On Thu, Sep 18, 2025 at 10:04 PM Rob Herring <robh@kernel.org> wrote:
> > > > >
> > > > > On Thu, Sep 18, 2025 at 05:52:31PM +0200, Dario Binacchi wrote:
> > > > > > Add support for glitch threshold configuration. A detected signal is valid
> > > > > > only if it lasts longer than the set threshold; otherwise, it is regarded
> > > > > > as a glitch.
> > > > > >
> > > > > > Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com>
> > > > > > Acked-by: Conor Dooley <conor.dooley@microchip.com>
> > > > > >
> > > > > > ---
> > > > > >
> > > > > > Changes in v5:
> > > > > > - Add Acked-by tag of Conor Dooley
> > > > > >
> > > > > > Changes in v2:
> > > > > > - Added in v2.
> > > > > >
> > > > > >  .../devicetree/bindings/input/touchscreen/touchscreen.yaml    | 4 ++++
> > > > > >  1 file changed, 4 insertions(+)
> > > > > >
> > > > > > diff --git a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > > > > index 3e3572aa483a..a60b4d08620d 100644
> > > > > > --- a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > > > > +++ b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > > > > @@ -206,6 +206,10 @@ properties:
> > > > > >
> > > > > >          unevaluatedProperties: false
> > > > > >
> > > > > > +  touchscreen-glitch-threshold-ns:
> > > > > > +    description: Minimum duration in nanoseconds a signal must remain stable
> > > > > > +      to be considered valid.
> > > > >
> > > > > What's wrong with debounce-delay-ms?
> > > >
> > > > Do you mean that I should rename touchscreen-glitch-threshold-ns to
> > > > debounce-delay-ms?
> > >
> > > I mean that's the common property we already have, so use it or explain
> > > why you aren't using it. I suppose the definition is technically a bit
> > > different if it's purely a s/w delay vs. h/w monitoring of the signal
> > > state. I don't think it matters if the interpretation by each driver is
> > > a bit different.
> > >
> > > Maybe msec is not enough resolution for you could be another reason?
> >
> > Yes, this is the main reason. As specified in the following patch:
> >   v5 4/6 dt-bindings: touchscreen: fsl,imx6ul-tsc: support glitch threshold
> >
> > Drivers must convert this value to IPG clock cycles and map
> > it to one of the four discrete thresholds exposed by the
> > TSC_DEBUG_MODE2 register:
> >
> >   0: 8191 IPG cycles
> >   1: 4095 IPG cycles
> >   2: 2047 IPG cycles
> >   3: 1023 IPG cycles
> >
> > In my case, the IPG clock runs at 66 MHz, which corresponds to:
> >
> > 124 µs for 0
> > 62 µs for 1
> > 31 us for 2
> > 15 us for 3
> >
> > So using milliseconds would not fit my use case. A possible trade-off
> > could be to use debounce-delay-us. Would that be acceptable?
>
> I agree it wouldn't map to what the h/w provides, but is what the h/w
> provides actually useful? There's plenty of h/w designed that's not
> useful. 15us is quite short for a glitch. Do you have an actual cases
> where the different values above are needed?

Considering an IPG clock at 66 MHz, currently at reset the deglitch
filter is set to 124 µs,
the driver sets it to 31 µs with a hardcoded value, and in my use case
I need to set it to 62 µs,
as you can see in the patch:
https://lore.kernel.org/all/20250918155240.2536852-6-dario.binacchi@amarulasolutions.com/
and its handling in
https://lore.kernel.org/all/20250918155240.2536852-7-dario.binacchi@amarulasolutions.com/

Another option could be to use a specific binding for the
fsl,imx6ul-tsc controller, as I did in the
earlier versions of the series.

Thanks and regards,
Dario

>
> Rob



-- 

Dario Binacchi

Senior Embedded Linux Developer

dario.binacchi@amarulasolutions.com

__________________________________


Amarula Solutions SRL

Via Le Canevare 30, 31100 Treviso, Veneto, IT

T. +39 042 243 5310
info@amarulasolutions.com

www.amarulasolutions.com

Re: [PATCH v5 3/6] dt-bindings: touchscreen: add touchscreen-glitch-threshold-ns property

[Rob Herring]

On Sat, Sep 20, 2025 at 11:39:59AM +0200, Dario Binacchi wrote:
> On Fri, Sep 19, 2025 at 10:44 PM Rob Herring <robh@kernel.org> wrote:
> >
> > On Fri, Sep 19, 2025 at 05:12:42PM +0200, Dario Binacchi wrote:
> > > On Fri, Sep 19, 2025 at 4:38 PM Rob Herring <robh@kernel.org> wrote:
> > > >
> > > > On Thu, Sep 18, 2025 at 10:37:37PM +0200, Dario Binacchi wrote:
> > > > > On Thu, Sep 18, 2025 at 10:04 PM Rob Herring <robh@kernel.org> wrote:
> > > > > >
> > > > > > On Thu, Sep 18, 2025 at 05:52:31PM +0200, Dario Binacchi wrote:
> > > > > > > Add support for glitch threshold configuration. A detected signal is valid
> > > > > > > only if it lasts longer than the set threshold; otherwise, it is regarded
> > > > > > > as a glitch.
> > > > > > >
> > > > > > > Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com>
> > > > > > > Acked-by: Conor Dooley <conor.dooley@microchip.com>
> > > > > > >
> > > > > > > ---
> > > > > > >
> > > > > > > Changes in v5:
> > > > > > > - Add Acked-by tag of Conor Dooley
> > > > > > >
> > > > > > > Changes in v2:
> > > > > > > - Added in v2.
> > > > > > >
> > > > > > >  .../devicetree/bindings/input/touchscreen/touchscreen.yaml    | 4 ++++
> > > > > > >  1 file changed, 4 insertions(+)
> > > > > > >
> > > > > > > diff --git a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > > > > > index 3e3572aa483a..a60b4d08620d 100644
> > > > > > > --- a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > > > > > +++ b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
> > > > > > > @@ -206,6 +206,10 @@ properties:
> > > > > > >
> > > > > > >          unevaluatedProperties: false
> > > > > > >
> > > > > > > +  touchscreen-glitch-threshold-ns:
> > > > > > > +    description: Minimum duration in nanoseconds a signal must remain stable
> > > > > > > +      to be considered valid.
> > > > > >
> > > > > > What's wrong with debounce-delay-ms?
> > > > >
> > > > > Do you mean that I should rename touchscreen-glitch-threshold-ns to
> > > > > debounce-delay-ms?
> > > >
> > > > I mean that's the common property we already have, so use it or explain
> > > > why you aren't using it. I suppose the definition is technically a bit
> > > > different if it's purely a s/w delay vs. h/w monitoring of the signal
> > > > state. I don't think it matters if the interpretation by each driver is
> > > > a bit different.
> > > >
> > > > Maybe msec is not enough resolution for you could be another reason?
> > >
> > > Yes, this is the main reason. As specified in the following patch:
> > >   v5 4/6 dt-bindings: touchscreen: fsl,imx6ul-tsc: support glitch threshold
> > >
> > > Drivers must convert this value to IPG clock cycles and map
> > > it to one of the four discrete thresholds exposed by the
> > > TSC_DEBUG_MODE2 register:
> > >
> > >   0: 8191 IPG cycles
> > >   1: 4095 IPG cycles
> > >   2: 2047 IPG cycles
> > >   3: 1023 IPG cycles
> > >
> > > In my case, the IPG clock runs at 66 MHz, which corresponds to:
> > >
> > > 124 µs for 0
> > > 62 µs for 1
> > > 31 us for 2
> > > 15 us for 3
> > >
> > > So using milliseconds would not fit my use case. A possible trade-off
> > > could be to use debounce-delay-us. Would that be acceptable?
> >
> > I agree it wouldn't map to what the h/w provides, but is what the h/w
> > provides actually useful? There's plenty of h/w designed that's not
> > useful. 15us is quite short for a glitch. Do you have an actual cases
> > where the different values above are needed?
> 
> Considering an IPG clock at 66 MHz, currently at reset the deglitch
> filter is set to 124 µs,
> the driver sets it to 31 µs with a hardcoded value, and in my use case
> I need to set it to 62 µs,

It would be helpful if the commit message explained why. What platform 
needs it and what happens without this support added?

> as you can see in the patch:
> https://lore.kernel.org/all/20250918155240.2536852-6-dario.binacchi@amarulasolutions.com/
> and its handling in
> https://lore.kernel.org/all/20250918155240.2536852-7-dario.binacchi@amarulasolutions.com/
> 
> Another option could be to use a specific binding for the
> fsl,imx6ul-tsc controller, as I did in the
> earlier versions of the series.

No, add debounce-delay-us to the common binding.

Rob