mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Frederic Weisbecker <frederic@kernel.org>
To: Stian Halseth <stian@itx.no>
Cc: Peter Zijlstra <peterz@infradead.org>,
	Paul Menzel <pmenzel@molgen.mpg.de>,
	Thomas Gleixner <tglx@kernel.org>,
	Anna-Maria Behnsen <anna-maria@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>,
	Shrikanth Hegde <sshegde@linux.ibm.com>,
	regressions@lists.linux.dev, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] sched/cputime: Don't warn when the tick period starts after idle exit
Date: Sat, 31 Oct 2026 14:54:41 +0100	[thread overview]
Message-ID: <auXzIbzU9aWBD_fM@pavilion.home> (raw)
In-Reply-To: <68f0450d47577dc4f83d32e5b0211c97ee8d24bd.camel@itx.no>

Le Wed, Oct 28, 2026 at 06:37:22PM +0100, Stian Halseth a écrit :
> Hi Frederic,
> 
> On Wed, 2026-10-28 at 15:14 +0100, Frederic Weisbecker wrote:
> > 
> > So let me depict that:
> > 
> > // clocksource = jiffies ?
> > // clockevent = lapic ?
> > tick_setup_device()
> >    tick_next_period = ktime_get() // jiffies_to_nsecs(jiffies)
> > 
> > tick_periodic()
> >    tick_next_period += TICK_NSECS
> >    jiffies++ // ktime_get() == tick_next_period
> > 
> > // jiffies > tsc_early
> > clocksource_select()
> > 
> > tick_periodic()
> >    //one tick has passed, so ktime_get() == jiffies + 1
> 
> Here is where it goes wrong. One tick has passed in real time, but not
> in ktime. The switch happened d after the last tick, jiffies never
> counted that d, and the tsc only counts from the switch on, so here
> ktime_get() == jiffies + TICK_NSEC - d.

So that assume that during the clocksource switch, the new clock synchronize
with the old one so that ktime_get() from the new clock should start from the
last value of the old clock. I'm having troubles to verify if
tk_setup_internals() does exactly that. Trying to recollect the few pieces of
my brain lost in the process.

I just added this patch to see what happens in practice:

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index ea2e6e55f37b..e8f3fc435933 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1854,6 +1854,7 @@ static int change_clocksource(void *data)
 {
 	struct clocksource *new = data, *old = NULL;
 
+	printk("old= %lld\n", ktime_get());
 	/*
 	 * If the clocksource is in a module, get a module reference.
 	 * Succeeds for built-in code (owner == NULL) as well. Abort if the
@@ -1876,7 +1877,7 @@ static int change_clocksource(void *data)
 		tk_setup_internals(tks, new);
 		timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL);
 	}
-
+	printk("new= %lld\n", ktime_get());
 	tk_aux_update_clocksource();
 
 	if (old) {

And I get this dump when jiffies switched to tsc_early:

[    1.549194] old= 1352575566
[    1.549930] new= 1352578748
[    1.550636] clocksource: Switched to clocksource tsc-early

That's 3 us, it could be the simple difference between the 2 printk.

But the switch from tsc-early to tsc is much more:

[    2.639818] old= 2445754540
[    2.640172] new= 2446107950
[    2.640927] clocksource: Switched to clocksource tsc

That's 353 us.

What do you think?

  reply	other threads:[~2026-10-31 13:54 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-10-07 14:29 [PATCH v3] sched/cputime: Don't account idle time twice after dyntick-idle Stian Halseth
2026-10-14 12:17 ` Frederic Weisbecker
2026-10-16  8:01 ` [tip: sched/core] " tip-bot2 for Stian Halseth
2026-10-25  7:27 ` WARNING: kernel/sched/cputime.c:481 at kcpustat_dyntick_stop+0x8b/0xa0, CPU#0: swapper/0/0 (was: [PATCH v3] sched/cputime: Don't account idle time twice after dyntick-idle) Paul Menzel
2026-10-25  8:13   ` Stian Halseth
2026-10-25 10:02   ` [PATCH] sched/cputime: Don't warn when the tick period starts after idle exit Stian Halseth
2026-10-26 16:42     ` Frederic Weisbecker
2026-10-26 17:28       ` Stian Halseth
2026-10-27 17:06         ` Frederic Weisbecker
2026-10-27 19:05           ` Stian Halseth
2026-10-28 14:14             ` Frederic Weisbecker
2026-10-28 17:37               ` Stian Halseth
2026-10-31 13:54                 ` Frederic Weisbecker [this message]
2026-10-31 14:11                   ` Stian Halseth
2026-10-30 16:14     ` Breno Leitao
2026-10-30 20:48       ` Stian Halseth

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=auXzIbzU9aWBD_fM@pavilion.home \
    --to=frederic@kernel.org \
    --cc=anna-maria@linutronix.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=pmenzel@molgen.mpg.de \
    --cc=regressions@lists.linux.dev \
    --cc=sshegde@linux.ibm.com \
    --cc=stian@itx.no \
    --cc=tglx@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

all inboxes | Powered by JetHome®