[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 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 5/6] ARM: dts: imx6ull-engicam-microgea-bmm: set touchscreen glitch threshold

[Dario Binacchi]

This way the detected signal is valid only if it lasts longer than
62 µs, otherwise it is not sampled.

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

---

Changes in v5:
- Add Reviewed-by tag of Frank Li

 arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea-bmm.dts | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea-bmm.dts b/arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea-bmm.dts
index 279d46c22cd7..f12084d8f2a0 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea-bmm.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea-bmm.dts
@@ -154,6 +154,7 @@ &tsc {
 	pinctrl-0 = <&pinctrl_tsc>;
 	measure-delay-time = <0x9ffff>;
 	pre-charge-time = <0xfff>;
+	touchscreen-glitch-threshold-ns = <62000>;
 	xnur-gpios = <&gpio1 3 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
-- 
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