Hello,
On Fri, Dec 07, 2018 at 05:29:30PM +0900, Yoshihiro Shimoda wrote:
> This patch adds support for "atomic" API. Behavior is the same as
> when using legacy APIs.
>
> Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@xxxxxxxxxxx>
> ---
> drivers/pwm/pwm-rcar.c | 32 ++++++++++++++++++++++++++++++++
> 1 file changed, 32 insertions(+)
>
> diff --git a/drivers/pwm/pwm-rcar.c b/drivers/pwm/pwm-rcar.c
> index 9cf4567..a5ea0f3 100644
> --- a/drivers/pwm/pwm-rcar.c
> +++ b/drivers/pwm/pwm-rcar.c
> @@ -200,12 +200,44 @@ static void rcar_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
> rcar_pwm_update(rp, RCAR_PWMCR_EN0, 0, RCAR_PWMCR);
> }
>
> +static int rcar_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
> + struct pwm_state *state)
> +{
> + struct rcar_pwm_chip *rp = to_rcar_pwm_chip(chip);
> + int div, ret;
> +
> + div = rcar_pwm_get_clock_division(rp, state->period);
> + if (div < 0)
> + return div;
> +
> + rcar_pwm_update(rp, RCAR_PWMCR_SYNC, RCAR_PWMCR_SYNC, RCAR_PWMCR);
> +
> + rcar_pwm_calc_counter(rp, div, state->duty_cycle, state->period);
> + ret = rcar_pwm_set_counter(rp);
> + if (!ret)
> + rcar_pwm_set_clock_control(rp, div);
> +
> + /* The SYNC should be set to 0 even if rcar_pwm_set_counter failed */
> + rcar_pwm_update(rp, RCAR_PWMCR_SYNC, 0, RCAR_PWMCR);
> +
> + if (!ret && state->enabled)
> + ret = rcar_pwm_enable(chip, pwm);
> +
> + if (!state->enabled) {
> + rcar_pwm_disable(chip, pwm);
> + ret = 0;
> + }
> +
> + return ret;
state->polarity isn't used here which is a bug I think.
Is the documentation for this hardware publically available?
If the pwm runs at say 30% duty cycle and then pwm_apply is called with
.period = 1000,
.duty_cycle = 600,
.enabled = false,
can it happen that for some time a duty cycle of 60% is provided? If so,
that's a bug.
Out of interest: How does the output behave if you disable the hardware?
Does it give a 0, or high-z?
Best regards
Uwe
--
Pengutronix e.K. | Uwe Kleine-König |
Industrial Linux Solutions | http://www.pengutronix.de/ |
