All of lore.kernel.org
 help / color / mirror / Atom feed
From: Frederic Weisbecker <frederic@kernel.org>
To: Peter Zijlstra <peterz@infradead.org>,
	Thomas Gleixner <tglx@linutronix.de>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Yunfeng Ye <yeyunfeng@huawei.com>,
	"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
	Frederic Weisbecker <frederic@kernel.org>,
	Marcelo Tosatti <mtosatti@redhat.com>
Subject: [PATCH 4/8] tick/nohz: Update idle_exittime on actual idle exit
Date: Thu, 22 Apr 2021 14:01:54 +0200	[thread overview]
Message-ID: <20210422120158.33629-5-frederic@kernel.org> (raw)
In-Reply-To: <20210422120158.33629-1-frederic@kernel.org>

From: Yunfeng Ye <yeyunfeng@huawei.com>

The idle_exittime field of tick_sched is used to record the time when
the idle state was left. but currently the idle_exittime is updated in
the function tick_nohz_restart_sched_tick(), which is not always in idle
state when nohz_full is configured:

  tick_irq_exit
    tick_nohz_irq_exit
      tick_nohz_full_update_tick
        tick_nohz_restart_sched_tick
          ts->idle_exittime = now;

It's thus overwritten by mistake on nohz_full tick restart. Move the
update to the appropriate idle exit path instead.

Signed-off-by: Yunfeng Ye <yeyunfeng@huawei.com>
Cc: Yunfeng Ye <yeyunfeng@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
 kernel/time/tick-sched.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 31efd55ed302..ffc13b9dfbe3 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -921,8 +921,6 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
 	 * Cancel the scheduled timer and restore the tick
 	 */
 	ts->tick_stopped  = 0;
-	ts->idle_exittime = now;
-
 	tick_nohz_restart(ts, now);
 }
 
@@ -1190,10 +1188,13 @@ unsigned long tick_nohz_get_idle_calls(void)
 	return ts->idle_calls;
 }
 
-static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
+static void tick_nohz_account_idle_time(struct tick_sched *ts,
+					ktime_t now)
 {
 	unsigned long ticks;
 
+	ts->idle_exittime = now;
+
 	if (vtime_accounting_enabled_this_cpu())
 		return;
 	/*
@@ -1214,8 +1215,9 @@ void tick_nohz_idle_restart_tick(void)
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	if (ts->tick_stopped) {
-		tick_nohz_restart_sched_tick(ts, ktime_get());
-		tick_nohz_account_idle_ticks(ts);
+		ktime_t now = ktime_get();
+		tick_nohz_restart_sched_tick(ts, now);
+		tick_nohz_account_idle_time(ts, now);
 	}
 }
 
@@ -1226,7 +1228,7 @@ static void tick_nohz_idle_update_tick(struct tick_sched *ts, ktime_t now)
 	else
 		tick_nohz_restart_sched_tick(ts, now);
 
-	tick_nohz_account_idle_ticks(ts);
+	tick_nohz_account_idle_time(ts, now);
 }
 
 /**
-- 
2.25.1


  parent reply	other threads:[~2021-04-22 12:02 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-22 12:01 [PATCH 0/8] tick/nohz updates v2 Frederic Weisbecker
2021-04-22 12:01 ` [PATCH 1/8] tick/nohz: Evaluate the CPU expression after the static key Frederic Weisbecker
2021-05-04 12:31   ` Peter Zijlstra
2021-04-22 12:01 ` [PATCH 2/8] tick/nohz: Conditionally restart tick on idle exit Frederic Weisbecker
2021-04-22 12:01 ` [PATCH 3/8] tick/nohz: Remove superflous check for CONFIG_VIRT_CPU_ACCOUNTING_NATIVE Frederic Weisbecker
2021-05-04 12:40   ` Peter Zijlstra
2021-04-22 12:01 ` Frederic Weisbecker [this message]
2021-04-22 12:01 ` [PATCH 5/8] tick/nohz: Update nohz_full Kconfig help Frederic Weisbecker
2021-04-22 12:01 ` [PATCH 6/8] tick/nohz: Only wakeup a single target cpu when kicking a task Frederic Weisbecker
2021-05-05 13:43   ` Peter Zijlstra
2021-05-10 10:39     ` Frederic Weisbecker
2021-05-10 10:48       ` Peter Zijlstra
2021-05-10 10:54         ` Frederic Weisbecker
2021-04-22 12:01 ` [PATCH 7/8] tick/nohz: Change signal tick dependency to wakeup CPUs of member tasks Frederic Weisbecker
2021-04-22 12:01 ` [PATCH 8/8] tick/nohz: Kick only _queued_ task whose tick dependency is updated Frederic Weisbecker
2021-05-05 13:57   ` Peter Zijlstra
2021-05-10 10:52     ` Frederic Weisbecker
2021-05-05 13:57 ` [PATCH 0/8] tick/nohz updates v2 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=20210422120158.33629-5-frederic@kernel.org \
    --to=frederic@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mtosatti@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rafael.j.wysocki@intel.com \
    --cc=tglx@linutronix.de \
    --cc=yeyunfeng@huawei.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.