From: Thomas Gleixner <tglx@linutronix.de>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
x86@kernel.org, Sebastian Siewior <bigeasy@linutronix.de>,
Anna-Maria Gleixner <anna-maria@linutronix.de>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Jiri Olsa <jolsa@redhat.com>, Paolo Bonzini <pbonzini@redhat.com>,
Juergen Gross <jgross@suse.com>
Subject: Re: [patch 10/12] hrtimer: Determine hard/soft expiry mode for hrtimer sleepers on RT
Date: Fri, 26 Jul 2019 22:52:18 +0200 (CEST) [thread overview]
Message-ID: <alpine.DEB.2.21.1907262249210.1791@nanos.tec.linutronix.de> (raw)
In-Reply-To: <20190726164428.40a4e4b4@gandalf.local.home>
On Fri, 26 Jul 2019, Steven Rostedt wrote:
> On Fri, 26 Jul 2019 20:30:58 +0200
> Thomas Gleixner <tglx@linutronix.de> wrote:
>
> > +++ b/kernel/time/hrtimer.c
> > @@ -1662,6 +1662,30 @@ static enum hrtimer_restart hrtimer_wake
> > static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
> > clockid_t clock_id, enum hrtimer_mode mode)
> > {
> > + /*
> > + * On PREEMPT_RT enabled kernels hrtimers which are not explicitely
> > + * marked for hard interrupt expiry mode are moved into soft
> > + * interrupt context either for latency reasons or because the
> > + * hrtimer callback takes regular spinlocks or invokes other
> > + * functions which are not suitable for hard interrupt context on
> > + * PREEMPT_RT.
>
> Have we marked all timer handlers that have normal spin_locks as
> HRTIMER_MODE_SOFT? Otherwise, can't we switch one to hard below and
> having their handler grab a spin_lock/mutex in hard interrupt context
> in RT?
See patch 09/12. We move all timers into soft mode which are not marked
MODE_HARD.
> > + *
> > + * The hrtimer_sleeper callback is RT compatible in hard interrupt
^^^^^^^^^^^^^^
> > + * context, but there is a latency concern: Untrusted userspace can
> > + * spawn many threads which arm timers for the same expiry time on
> > + * the same CPU. That causes a latency spike due to the wakeup of
> > + * a gazillion threads.
> > + *
> > + * OTOH, priviledged real-time user space applications rely on the
> > + * low latency of hard interrupt wakeups. If the current task is in
> > + * a real-time scheduling class, mark the mode for hard interrupt
> > + * expiry.
> > + */
> > + if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
> > + if (task_is_realtime(current) && !(mode & HRTIMER_MODE_SOFT))
> > + mode |= HRTIMER_MODE_HARD;
> > + }
> > +
> > __hrtimer_init(&sl->timer, clock_id, mode);
> > sl->timer.function = hrtimer_wakeup;
It's the wakeup function and nothing is supposed to override that.
Thanks,
tglx
next prev parent reply other threads:[~2019-07-26 20:52 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-26 18:30 [patch 00/12] (hr)timers: Prepare for PREEMPT_RT support Thomas Gleixner
2019-07-26 18:30 ` [patch 01/12] hrtimer: Remove task argument from hrtimer_init_sleeper() Thomas Gleixner
2019-07-26 19:57 ` Steven Rostedt
2019-07-26 20:01 ` Thomas Gleixner
2019-07-30 22:07 ` [tip:timers/core] " tip-bot for Thomas Gleixner
2019-07-26 18:30 ` [patch 02/12] hrtimer: Consolidate hrtimer_init() + hrtimer_init_sleeper() calls Thomas Gleixner
2019-07-30 22:08 ` [tip:timers/core] " tip-bot for Sebastian Andrzej Siewior
2019-08-01 15:49 ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 03/12] hrtimer: Introduce HARD expiry mode Thomas Gleixner
2019-07-30 22:10 ` [tip:timers/core] " tip-bot for Sebastian Andrzej Siewior
2019-08-01 15:52 ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 04/12] sched: Mark hrtimers to expire in hard interrupt context Thomas Gleixner
2019-07-30 22:11 ` [tip:timers/core] " tip-bot for Thomas Gleixner
2019-08-01 15:53 ` tip-bot for Sebastian Andrzej Siewior
2019-08-01 18:58 ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 05/12] perf/core: " Thomas Gleixner
2019-07-30 22:12 ` [tip:timers/core] " tip-bot for Thomas Gleixner
2019-08-01 15:54 ` tip-bot for Sebastian Andrzej Siewior
2019-08-01 18:59 ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 06/12] watchdog: Mark watchdog_hrtimer " Thomas Gleixner
2019-07-30 22:13 ` [tip:timers/core] " tip-bot for Sebastian Andrzej Siewior
2019-08-01 15:55 ` tip-bot for Sebastian Andrzej Siewior
2019-08-01 19:00 ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 07/12] KVM: LAPIC: Mark hrtimer " Thomas Gleixner
2019-07-26 19:41 ` Paolo Bonzini
2019-07-30 22:14 ` [tip:timers/core] " tip-bot for Sebastian Andrzej Siewior
2019-08-01 15:55 ` tip-bot for Sebastian Andrzej Siewior
2019-08-01 19:01 ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 08/12] tick: Mark tick related hrtimers to expiry " Thomas Gleixner
2019-07-30 22:14 ` [tip:timers/core] " tip-bot for Sebastian Andrzej Siewior
2019-08-01 15:56 ` tip-bot for Sebastian Andrzej Siewior
2019-08-01 19:01 ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 09/12] hrtimer: Move unmarked hrtimers to soft interrupt expiry on RT Thomas Gleixner
2019-07-30 22:15 ` [tip:timers/core] " tip-bot for Sebastian Andrzej Siewior
2019-08-01 15:57 ` tip-bot for Sebastian Andrzej Siewior
2019-08-01 19:02 ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 10/12] hrtimer: Determine hard/soft expiry mode for hrtimer sleepers " Thomas Gleixner
2019-07-26 20:44 ` Steven Rostedt
2019-07-26 20:52 ` Thomas Gleixner [this message]
2019-07-26 20:56 ` Steven Rostedt
2019-07-26 21:16 ` Julia Cartwright
2019-07-26 21:30 ` Steven Rostedt
2019-07-26 21:35 ` Thomas Gleixner
2019-07-30 22:16 ` [tip:timers/core] " tip-bot for Sebastian Andrzej Siewior
2019-08-01 15:58 ` tip-bot for Sebastian Andrzej Siewior
2019-08-01 19:03 ` tip-bot for Sebastian Andrzej Siewior
2019-07-26 18:30 ` [patch 11/12] hrtimer: Prepare support for PREEMPT_RT Thomas Gleixner
2019-07-28 9:06 ` Juergen Gross
2019-07-29 15:08 ` Steven Rostedt
2019-07-29 17:30 ` Paolo Bonzini
2019-07-31 8:45 ` Juergen Gross
2019-07-30 22:17 ` [tip:timers/core] " tip-bot for Anna-Maria Gleixner
2019-08-01 15:58 ` tip-bot for Anna-Maria Gleixner
2019-08-01 19:04 ` tip-bot for Anna-Maria Gleixner
2019-08-20 13:26 ` Frederic Weisbecker
2019-08-23 2:12 ` [tip: timers/core] hrtimer: Improve comments on handling priority inversion against softirq kthread tip-bot2 for Frederic Weisbecker
2019-07-26 18:31 ` [patch 12/12] timers: Prepare support for PREEMPT_RT Thomas Gleixner
2019-07-30 22:17 ` [tip:timers/core] " tip-bot for Anna-Maria Gleixner
2019-08-01 15:59 ` tip-bot for Anna-Maria Gleixner
2019-08-01 19:04 ` tip-bot for Anna-Maria Gleixner
2019-07-29 19:45 ` [patch 00/12] (hr)timers: Prepare for PREEMPT_RT support Peter Zijlstra
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=alpine.DEB.2.21.1907262249210.1791@nanos.tec.linutronix.de \
--to=tglx@linutronix.de \
--cc=acme@kernel.org \
--cc=anna-maria@linutronix.de \
--cc=bigeasy@linutronix.de \
--cc=jgross@suse.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=rostedt@goodmis.org \
--cc=x86@kernel.org \
/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).