The ARR register is cleared unconditionally upon probing, after the maximum
value has been read. This initial condition is rather not intuitive, when
considering the counter child driver. It rather expects the maximum value
by default:
- The counter interface shows a zero value by default for 'ceiling'
attribute.
- Enabling the counter without any prior configuration makes it doesn't
count.
The reset value of ARR register is the maximum. So Choice here
is to backup it, and restore it then, instead of clearing its value.
It also fixes the initial condition seen by the counter driver.
Fixes: d0f949e220fd ("mfd: Add STM32 Timers driver")
Signed-off-by: Fabrice Gasnier <[email protected]>
---
drivers/mfd/stm32-timers.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/mfd/stm32-timers.c b/drivers/mfd/stm32-timers.c
index add6033..44ed2fc 100644
--- a/drivers/mfd/stm32-timers.c
+++ b/drivers/mfd/stm32-timers.c
@@ -158,13 +158,18 @@ static const struct regmap_config stm32_timers_regmap_cfg = {
static void stm32_timers_get_arr_size(struct stm32_timers *ddata)
{
+ u32 arr;
+
+ /* Backup ARR to restore it after getting the maximum value */
+ regmap_read(ddata->regmap, TIM_ARR, &arr);
+
/*
* Only the available bits will be written so when readback
* we get the maximum value of auto reload register
*/
regmap_write(ddata->regmap, TIM_ARR, ~0L);
regmap_read(ddata->regmap, TIM_ARR, &ddata->max_arr);
- regmap_write(ddata->regmap, TIM_ARR, 0x0);
+ regmap_write(ddata->regmap, TIM_ARR, arr);
}
static int stm32_timers_dma_probe(struct device *dev,
--
2.7.4
On Wed, Mar 03, 2021 at 06:51:35PM +0100, Fabrice Gasnier wrote:
> The ARR register is cleared unconditionally upon probing, after the maximum
> value has been read. This initial condition is rather not intuitive, when
> considering the counter child driver. It rather expects the maximum value
> by default:
> - The counter interface shows a zero value by default for 'ceiling'
> attribute.
> - Enabling the counter without any prior configuration makes it doesn't
> count.
>
> The reset value of ARR register is the maximum. So Choice here
> is to backup it, and restore it then, instead of clearing its value.
> It also fixes the initial condition seen by the counter driver.
>
> Fixes: d0f949e220fd ("mfd: Add STM32 Timers driver")
>
> Signed-off-by: Fabrice Gasnier <[email protected]>
Acked-by: William Breathitt Gray <[email protected]>
> ---
> drivers/mfd/stm32-timers.c | 7 ++++++-
> 1 file changed, 6 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/mfd/stm32-timers.c b/drivers/mfd/stm32-timers.c
> index add6033..44ed2fc 100644
> --- a/drivers/mfd/stm32-timers.c
> +++ b/drivers/mfd/stm32-timers.c
> @@ -158,13 +158,18 @@ static const struct regmap_config stm32_timers_regmap_cfg = {
>
> static void stm32_timers_get_arr_size(struct stm32_timers *ddata)
> {
> + u32 arr;
> +
> + /* Backup ARR to restore it after getting the maximum value */
> + regmap_read(ddata->regmap, TIM_ARR, &arr);
> +
> /*
> * Only the available bits will be written so when readback
> * we get the maximum value of auto reload register
> */
> regmap_write(ddata->regmap, TIM_ARR, ~0L);
> regmap_read(ddata->regmap, TIM_ARR, &ddata->max_arr);
> - regmap_write(ddata->regmap, TIM_ARR, 0x0);
> + regmap_write(ddata->regmap, TIM_ARR, arr);
> }
>
> static int stm32_timers_dma_probe(struct device *dev,
> --
> 2.7.4
>
On 3/3/21 6:51 PM, Fabrice Gasnier wrote:
> The ARR register is cleared unconditionally upon probing, after the maximum
> value has been read. This initial condition is rather not intuitive, when
> considering the counter child driver. It rather expects the maximum value
> by default:
> - The counter interface shows a zero value by default for 'ceiling'
> attribute.
> - Enabling the counter without any prior configuration makes it doesn't
> count.
>
> The reset value of ARR register is the maximum. So Choice here
> is to backup it, and restore it then, instead of clearing its value.
> It also fixes the initial condition seen by the counter driver.
>
> Fixes: d0f949e220fd ("mfd: Add STM32 Timers driver")
>
> Signed-off-by: Fabrice Gasnier <[email protected]>
> ---
> drivers/mfd/stm32-timers.c | 7 ++++++-
> 1 file changed, 6 insertions(+), 1 deletion(-)
Hi,
It's just a gentle reminder to review this patch.
Best Regards,
Fabrice
>
> diff --git a/drivers/mfd/stm32-timers.c b/drivers/mfd/stm32-timers.c
> index add6033..44ed2fc 100644
> --- a/drivers/mfd/stm32-timers.c
> +++ b/drivers/mfd/stm32-timers.c
> @@ -158,13 +158,18 @@ static const struct regmap_config stm32_timers_regmap_cfg = {
>
> static void stm32_timers_get_arr_size(struct stm32_timers *ddata)
> {
> + u32 arr;
> +
> + /* Backup ARR to restore it after getting the maximum value */
> + regmap_read(ddata->regmap, TIM_ARR, &arr);
> +
> /*
> * Only the available bits will be written so when readback
> * we get the maximum value of auto reload register
> */
> regmap_write(ddata->regmap, TIM_ARR, ~0L);
> regmap_read(ddata->regmap, TIM_ARR, &ddata->max_arr);
> - regmap_write(ddata->regmap, TIM_ARR, 0x0);
> + regmap_write(ddata->regmap, TIM_ARR, arr);
> }
>
> static int stm32_timers_dma_probe(struct device *dev,
>
On Mon, 22 Mar 2021, Fabrice Gasnier wrote:
> On 3/3/21 6:51 PM, Fabrice Gasnier wrote:
> > The ARR register is cleared unconditionally upon probing, after the maximum
> > value has been read. This initial condition is rather not intuitive, when
> > considering the counter child driver. It rather expects the maximum value
> > by default:
> > - The counter interface shows a zero value by default for 'ceiling'
> > attribute.
> > - Enabling the counter without any prior configuration makes it doesn't
> > count.
> >
> > The reset value of ARR register is the maximum. So Choice here
> > is to backup it, and restore it then, instead of clearing its value.
> > It also fixes the initial condition seen by the counter driver.
> >
> > Fixes: d0f949e220fd ("mfd: Add STM32 Timers driver")
> >
> > Signed-off-by: Fabrice Gasnier <[email protected]>
> > ---
> > drivers/mfd/stm32-timers.c | 7 ++++++-
> > 1 file changed, 6 insertions(+), 1 deletion(-)
>
> Hi,
>
> It's just a gentle reminder to review this patch.
Looks like this was either dropped, or didn't make it into my queue.
It's on the list now, I will deal with it soon.
> > diff --git a/drivers/mfd/stm32-timers.c b/drivers/mfd/stm32-timers.c
> > index add6033..44ed2fc 100644
> > --- a/drivers/mfd/stm32-timers.c
> > +++ b/drivers/mfd/stm32-timers.c
> > @@ -158,13 +158,18 @@ static const struct regmap_config stm32_timers_regmap_cfg = {
> >
> > static void stm32_timers_get_arr_size(struct stm32_timers *ddata)
> > {
> > + u32 arr;
> > +
> > + /* Backup ARR to restore it after getting the maximum value */
> > + regmap_read(ddata->regmap, TIM_ARR, &arr);
> > +
> > /*
> > * Only the available bits will be written so when readback
> > * we get the maximum value of auto reload register
> > */
> > regmap_write(ddata->regmap, TIM_ARR, ~0L);
> > regmap_read(ddata->regmap, TIM_ARR, &ddata->max_arr);
> > - regmap_write(ddata->regmap, TIM_ARR, 0x0);
> > + regmap_write(ddata->regmap, TIM_ARR, arr);
> > }
> >
> > static int stm32_timers_dma_probe(struct device *dev,
> >
--
Lee Jones [李琼斯]
Senior Technical Lead - Developer Services
Linaro.org │ Open source software for Arm SoCs
Follow Linaro: Facebook | Twitter | Blog
On Wed, 03 Mar 2021, Fabrice Gasnier wrote:
> The ARR register is cleared unconditionally upon probing, after the maximum
> value has been read. This initial condition is rather not intuitive, when
> considering the counter child driver. It rather expects the maximum value
> by default:
> - The counter interface shows a zero value by default for 'ceiling'
> attribute.
> - Enabling the counter without any prior configuration makes it doesn't
> count.
>
> The reset value of ARR register is the maximum. So Choice here
> is to backup it, and restore it then, instead of clearing its value.
> It also fixes the initial condition seen by the counter driver.
>
> Fixes: d0f949e220fd ("mfd: Add STM32 Timers driver")
>
> Signed-off-by: Fabrice Gasnier <[email protected]>
> ---
> drivers/mfd/stm32-timers.c | 7 ++++++-
> 1 file changed, 6 insertions(+), 1 deletion(-)
Applied, thanks.
--
Lee Jones [李琼斯]
Senior Technical Lead - Developer Services
Linaro.org │ Open source software for Arm SoCs
Follow Linaro: Facebook | Twitter | Blog