From: Thomas Gleixner <tglx@linutronix.de>
To: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Anna-Maria Behnsen <anna-maria@linutronix.de>,
linux-kernel@vger.kernel.org,
Frederic Weisbecker <frederic@kernel.org>,
Peter Xu <peterx@redhat.com>,
Nitesh Narayan Lal <nitesh@redhat.com>,
Alex Belits <abelits@marvell.com>
Subject: Re: [PATCH v2] hrtimer: avoid retrigger_next_event IPI
Date: Wed, 14 Apr 2021 19:19:43 +0200 [thread overview]
Message-ID: <874kg8wzps.ffs@nanos.tec.linutronix.de> (raw)
In-Reply-To: <20210413170431.GA16190@fuller.cnet>
Marcelo,
On Tue, Apr 13 2021 at 14:04, Marcelo Tosatti wrote:
> Setting the realtime clock triggers an IPI to all CPUs to reprogram
> hrtimers.
s/hrtimers/clock event device/
> However, only realtime and TAI clocks have their offsets updated
> (and therefore potentially require a reprogram).
>
> Check if it only has monotonic active timers, and in that case
boottime != monotonic
> update the realtime and TAI base offsets remotely, skipping the IPI.
Something like this perhaps:
Instead of sending an IPI unconditionally, check each per CPU hrtimer base
whether it has active timers in the CLOCK_REALTIME and CLOCK_TAI bases. If
that's not the case, update the realtime and TAI base offsets remotely and
skip the IPI. This ensures that any subsequently armed timers on
CLOCK_REALTIME and CLOCK_TAI are evaluated with the correct offsets.
Hmm?
> +#define CLOCK_SET_BASES ((1U << HRTIMER_BASE_REALTIME)| \
Missing space between ) and |
> + (1U << HRTIMER_BASE_REALTIME_SOFT)| \
> + (1U << HRTIMER_BASE_TAI)| \
> + (1U << HRTIMER_BASE_TAI_SOFT))
> +
> +static bool need_reprogram_timer(struct hrtimer_cpu_base *cpu_base)
> +{
> + unsigned int active = 0;
> +
> + if (cpu_base->softirq_activated)
> + return true;
> +
> + active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT;
> +
> + active = active | (cpu_base->active_bases & HRTIMER_ACTIVE_HARD);
> +
> + if ((active & CLOCK_SET_BASES) == 0)
> + return false;
> +
> + return true;
That's a pretty elaborate way of writing:
return (cpu_base->active_bases & CLOCK_SET_BASES) != 0;
> +}
> +
> /*
> * Clock realtime was set
> *
> @@ -885,9 +907,31 @@ static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram)
> void clock_was_set(void)
> {
> #ifdef CONFIG_HIGH_RES_TIMERS
> - /* Retrigger the CPU local events everywhere */
> - on_each_cpu(retrigger_next_event, NULL, 1);
> + cpumask_var_t mask;
> + int cpu;
> +
> + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) {
> + on_each_cpu(retrigger_next_event, NULL, 1);
> + goto set_timerfd;
> + }
> +
> + /* Avoid interrupting CPUs if possible */
> + preempt_disable();
That preempt disable is only required around the function call, for the
loop cpus_read_lock() is sufficient.
> + for_each_online_cpu(cpu) {
> + unsigned long flags;
> + struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
> +
> + raw_spin_lock_irqsave(&cpu_base->lock, flags);
> + if (need_reprogram_timer(cpu_base))
> + cpumask_set_cpu(cpu, mask);
> + raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
> + }
> +
> + smp_call_function_many(mask, retrigger_next_event, NULL, 1);
> + preempt_enable();
> + free_cpumask_var(mask);
> #endif
> +set_timerfd:
My brain compiler tells me that with CONFIG_HIGH_RES_TIMERS=n a real
compiler will emit a warning about a defined, but unused label....
> timerfd_clock_was_set();
> }
Thanks,
tglx
next prev parent reply other threads:[~2021-04-14 17:19 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-07 13:53 [PATCH] hrtimer: avoid retrigger_next_event IPI Marcelo Tosatti
2021-04-07 19:28 ` kernel test robot
2021-04-07 22:14 ` Frederic Weisbecker
2021-04-08 12:27 ` Marcelo Tosatti
2021-04-09 14:15 ` Thomas Gleixner
2021-04-09 16:51 ` Marcelo Tosatti
2021-04-10 7:53 ` Thomas Gleixner
2021-04-13 17:04 ` [PATCH v2] " Marcelo Tosatti
2021-04-14 17:19 ` Thomas Gleixner [this message]
2021-04-15 15:39 ` [PATCH v3] " Marcelo Tosatti
2021-04-15 18:59 ` Thomas Gleixner
2021-04-15 20:40 ` [PATCH v4] " Marcelo Tosatti
2021-04-16 16:00 ` [PATCH v5] " Marcelo Tosatti
2021-04-16 17:13 ` Peter Xu
2021-04-17 16:24 ` Thomas Gleixner
2021-04-17 16:51 ` Thomas Gleixner
2021-04-19 18:56 ` Marcelo Tosatti
2021-04-19 19:39 ` [PATCH v6] " Marcelo Tosatti
2021-04-19 20:52 ` Thomas Gleixner
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=874kg8wzps.ffs@nanos.tec.linutronix.de \
--to=tglx@linutronix.de \
--cc=abelits@marvell.com \
--cc=anna-maria@linutronix.de \
--cc=frederic@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=nitesh@redhat.com \
--cc=peterx@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).