powerpc/watchdog: introduce a NMI watchdog's factor

Introduce a factor which would apply to the NMI watchdog timeout.

This factor is a percentage added to the watchdog_tresh value. The value is
set under the watchdog_mutex protection and lockup_detector_reconfigure()
is called to recompute wd_panic_timeout_tb.

Once the factor is set, it remains until it is set back to 0, which means
no impact.

Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220713154729.80789-4-ldufour@linux.ibm.com
This commit is contained in:
Laurent Dufour 2022-07-13 17:47:28 +02:00 committed by Michael Ellerman
parent 7c56a8733d
commit f5e74e8360
2 changed files with 22 additions and 1 deletions

View File

@ -5,8 +5,10 @@
#ifdef CONFIG_PPC_WATCHDOG
extern void arch_touch_nmi_watchdog(void);
long soft_nmi_interrupt(struct pt_regs *regs);
void watchdog_nmi_set_timeout_pct(u64 pct);
#else
static inline void arch_touch_nmi_watchdog(void) {}
static inline void watchdog_nmi_set_timeout_pct(u64 pct) {}
#endif
#ifdef CONFIG_NMI_IPI

View File

@ -91,6 +91,10 @@ static cpumask_t wd_smp_cpus_pending;
static cpumask_t wd_smp_cpus_stuck;
static u64 wd_smp_last_reset_tb;
#ifdef CONFIG_PPC_PSERIES
static u64 wd_timeout_pct;
#endif
/*
* Try to take the exclusive watchdog action / NMI IPI / printing lock.
* wd_smp_lock must be held. If this fails, we should return and wait
@ -527,7 +531,13 @@ static int stop_watchdog_on_cpu(unsigned int cpu)
static void watchdog_calc_timeouts(void)
{
wd_panic_timeout_tb = watchdog_thresh * ppc_tb_freq;
u64 threshold = watchdog_thresh;
#ifdef CONFIG_PPC_PSERIES
threshold += (READ_ONCE(wd_timeout_pct) * threshold) / 100;
#endif
wd_panic_timeout_tb = threshold * ppc_tb_freq;
/* Have the SMP detector trigger a bit later */
wd_smp_panic_timeout_tb = wd_panic_timeout_tb * 3 / 2;
@ -570,3 +580,12 @@ int __init watchdog_nmi_probe(void)
}
return 0;
}
#ifdef CONFIG_PPC_PSERIES
void watchdog_nmi_set_timeout_pct(u64 pct)
{
pr_info("Set the NMI watchdog timeout factor to %llu%%\n", pct);
WRITE_ONCE(wd_timeout_pct, pct);
lockup_detector_reconfigure();
}
#endif