| Message ID | 20250918155240.2536852-4-dario.binacchi@amarulasolutions.com |
|---|---|
| State | New |
| Headers | show |
| Series |
|
| Related | show |
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? To unsubscribe from this group and stop receiving emails from it, send an email to linux-amarula+unsubscribe@amarulasolutions.com.
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
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 To unsubscribe from this group and stop receiving emails from it, send an email to linux-amarula+unsubscribe@amarulasolutions.com.
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
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 To unsubscribe from this group and stop receiving emails from it, send an email to linux-amarula+unsubscribe@amarulasolutions.com.
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
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 ]