Re: [External] Re: [PATCH v3] sched/core: Adapt WARN_DOUBLE_CLOCK machinery for core-sched

[Hao Jia]

On 2023/3/31 Phil Auld wrote:
> Hi,
>
> On Thu, Mar 30, 2023 at 11:58:27AM +0800 Hao Jia wrote:
> > When sched_core_enabled(), we sometimes need to call update_rq_clock()
> > to update the rq clock of sibling CPUs on the same core, before that we
> > need to clear RQCF_UPDATED of rq->clock_update_flags to avoid the
> > WARN_DOUBLE_CLOCK warning. Because at this time the rq->clock_update_flags
> > of sibling CPUs may be RQCF_UPDATED. If sched_core_enabled(), we will get
> > a core wide rq->lock, so at this point we can safely clear RQCF_UPDATED of
> > rq->clock_update_flags of all CPUs on this core to avoid the
> > WARN_DOUBLE_CLOCK warning.
> >
> > We sometimes use rq_pin_lock() and raw_spin_rq_lock() separately,
> > For example newidle_balance() and _double_lock_balance(). We will
> > temporarily give up core wide rq->lock, and then use raw_spin_rq_lock()
> > to reacquire core wide rq->lock without rq_pin_lock(), so We can not
> > clear RQCF_UPDATED of rq->clock_update_flags of other cpus on the
> > same core in rq_pin_lock().
> >
> > Steps to reproduce:
> > 1. Enable CONFIG_SCHED_DEBUG and CONFIG_SCHED_CORE when compiling
> >     the kernel
> > 2. echo 1 > /sys/kernel/debug/clear_warn_once
> >     echo "WARN_DOUBLE_CLOCK" > /sys/kernel/debug/sched/features
> > 3. Run the linux/tools/testing/selftests/sched/cs_prctl_test test
> >
> > Signed-off-by: Hao Jia <jiahao.os@xxxxxxxxxxxxx>
>
> I think this looks good. One small nit is that I think you might
> replace "core wide" with "core-wide" everywhere.
>
>
> Reviewed-by: Phil Auld <pauld@xxxxxxxxxx>

Thank you for your review, I will do it in the next version.

Thanks,
Hao