linux-kernel - RE: [PATCH] watchdog: da9062: do not ping the hw during stop()

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <AM6PR10MB2263D6F62A45568D5671377D800A0@AM6PR10MB2263.EURPRD10.PROD.OUTLOOK.COM>
Date:   Tue, 28 Jan 2020 10:13:33 +0000
From:   Adam Thomson <Adam.Thomson.Opensource@...semi.com>
To:     Marco Felsch <m.felsch@...gutronix.de>,
        Support Opensource <Support.Opensource@...semi.com>,
        "linux@...ck-us.net" <linux@...ck-us.net>,
        Steve Twiss <stwiss.opensource@...semi.com>,
        Adam Thomson <Adam.Thomson.Opensource@...semi.com>
CC:     "linux-watchdog@...r.kernel.org" <linux-watchdog@...r.kernel.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "kernel@...gutronix.de" <kernel@...gutronix.de>
Subject: RE: [PATCH] watchdog: da9062: do not ping the hw during stop()

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@...gutronix.de>
> ---
>  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