Re: [PATCH v2 2/2] watchdog: w83627hf_wdt: Use WDOG_HW_RUNNING for running chip on boot

[sashiko-bot@kernel.org]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Removing the manual watchdog timeout reset during driver initialization while continuing to unconditionally force the hardware into 'seconds' mode causes a severe timeout truncation. If the BIOS left the watchdog running with a 'minutes' timebase (e.g., 5 minutes), the raw hardware register value (e.g., 5) is preserved but its unit is instantly reinterpreted as seconds, leaving a window of only 5 seconds before the watchdog fires.
--

commit 41d13e5a4078e3d18e184d179b1d408461a148bd
Author: Paul Louvel <paul.louvel@bootlin.com>

watchdog: w83627hf_wdt: Use WDOG_HW_RUNNING for running chip on boot

This commit replaces the manual watchdog refresh during initialization
with the WDOG_HW_RUNNING flag. It delegates keepalives to the watchdog core
when the device is already running on boot.

> diff --git a/drivers/watchdog/w83627hf_wdt.c b/drivers/watchdog/w83627hf_wdt.c
> index 1f649fda8a813..5348c0f79de8f 100644
> --- a/drivers/watchdog/w83627hf_wdt.c
> +++ b/drivers/watchdog/w83627hf_wdt.c
> @@ -240,9 +240,8 @@ static int w83627hf_init(struct watchdog_device *wdog, enum chips chip)
>  			pr_warn("Stopping previously enabled watchdog until userland kicks in\n");
>  			superio_outb(cr_wdt_timeout, 0);
>  		} else {
> -			pr_info("Watchdog already running. Resetting timeout to %d sec\n",
> -				wdog->timeout);
> -			superio_outb(cr_wdt_timeout, wdog->timeout);
> +			pr_info("Watchdog already running.\n");
> +			set_bit(WDOG_HW_RUNNING, &wdog->status);
>  		}
>  	}
>  

[Severity: High]
Does removing this timeout reset cause a timeout truncation issue?

Immediately after this block, w83627hf_init() forces the hardware timebase 
into seconds mode:

	/* set second mode & disable keyboard turning off watchdog */
	t = superio_inb(cr_wdt_control) & ~0x0C;
	superio_outb(cr_wdt_control, t);

If the BIOS previously left the watchdog running with a 'minutes' timebase 
(for example, 5 minutes), the raw hardware register value (5) is preserved.

However, because the timebase is instantly reinterpreted as seconds, the
system is left with a window of only 5 seconds before the watchdog fires.

This can lead to spurious reboots during the OS boot phase before the watchdog 
core or user space can issue the next ping.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260706-w83627hf_wdt-nct6126d-v2-0-77af74af88ae@bootlin.com?part=2