On 20 January 2020 09:17, Marco Felsch wrote:
> The da9062 hw has a minimum ping cool down phase of at least 200ms. The
> driver takes that into account by setting the min_hw_heartbeat_ms to
> 300ms and the core guarantees that the hw limit is observed for the
> ping() calls. But the core can't guarantees the required minimum ping
> cool down phase if a stop() command is send immediately after the ping()
> command. So it is not allowed to ping the watchdog within the stop()
> command as the driver do. Remove the ping can be done without doubts
> because the watchdog gets disabled anyway and a (re)start reset the
> watchdog counter too.
>
Good spot. Thanks for this. Am wondering if this might also be an issue for
da9062_wdt_set_timeout() which calls down to
da9062_wdt_update_timeout_register() which in turn pings the watchdog first
before disabling it and then setting the new timeout value. I think it makes
sense to remove the ping from da9062_wdt_update_timeout_register() as well to
avoid any possible issues where a ping() is called and then immediately after
there's a call to adjust the timeout. If you can double check my hypothesis
that would be good though.
> Signed-off-by: Marco Felsch <m.felsch@xxxxxxxxxxxxxx>
> ---
> drivers/watchdog/da9062_wdt.c | 7 -------
> 1 file changed, 7 deletions(-)
>
> diff --git a/drivers/watchdog/da9062_wdt.c b/drivers/watchdog/da9062_wdt.c
> index 77b6b5336067..0ad15d55071c 100644
> --- a/drivers/watchdog/da9062_wdt.c
> +++ b/drivers/watchdog/da9062_wdt.c
> @@ -97,13 +97,6 @@ static int da9062_wdt_stop(struct watchdog_device *wdd)
> struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd);
> int ret;
>
> - ret = da9062_reset_watchdog_timer(wdt);
> - if (ret) {
> - dev_err(wdt->hw->dev, "Failed to ping the watchdog (err =
> %d)\n",
> - ret);
> - return ret;
> - }
> -
> ret = regmap_update_bits(wdt->hw->regmap,
> DA9062AA_CONTROL_D,
> DA9062AA_TWDSCALE_MASK,
> --
> 2.20.1
