[PATCH v3 5/5] arm64: barrier: Handle waiting in smp_cond_load_relaxed_timewait()
Christoph Lameter (Ampere)
cl at gentwo.org
Mon Jun 30 09:33:43 PDT 2025
On Thu, 26 Jun 2025, Ankur Arora wrote:
> @@ -222,6 +223,53 @@ do { \
> #define __smp_timewait_store(ptr, val) \
> __cmpwait_relaxed(ptr, val)
>
> +/*
> + * Redefine ARCH_TIMER_EVT_STREAM_PERIOD_US locally to avoid include hell.
> + */
> +#define __ARCH_TIMER_EVT_STREAM_PERIOD_US 100UL
> +extern bool arch_timer_evtstrm_available(void);
> +
> +static inline u64 ___smp_cond_spinwait(u64 now, u64 prev, u64 end,
> + u32 *spin, bool *wait, u64 slack);
> +/*
> + * To minimize time spent spinning, we want to allow a large overshoot.
> + * So, choose a default slack value of the event-stream period.
> + */
> +#define SMP_TIMEWAIT_DEFAULT_US __ARCH_TIMER_EVT_STREAM_PERIOD_US
> +
> +static inline u64 ___smp_cond_timewait(u64 now, u64 prev, u64 end,
> + u32 *spin, bool *wait, u64 slack)
> +{
> + bool wfet = alternative_has_cap_unlikely(ARM64_HAS_WFXT);
> + bool wfe, ev = arch_timer_evtstrm_available();
An unitialized and initialized variable on the same line. Maybe separate
that. Looks confusing and unusual to me.
> + u64 evt_period = __ARCH_TIMER_EVT_STREAM_PERIOD_US;
> + u64 remaining = end - now;
> +
> + if (now >= end)
> + return 0;
> + /*
> + * Use WFE if there's enough slack to get an event-stream wakeup even
> + * if we don't come out of the WFE due to natural causes.
> + */
> + wfe = ev && ((remaining + slack) > evt_period);
The line above does not matter for the wfet case and the calculation is
ignored. We hope that in the future wfet will be the default case.
More information about the linux-arm-kernel
mailing list