linux-kernel - [PATCH 1/4] tick/sched: Forward timer even in nohz mode

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <1576538545-13274-1-git-send-email-swood@redhat.com>
Date:   Mon, 16 Dec 2019 18:22:22 -0500
From:   Scott Wood <swood@...hat.com>
To:     Peter Zijlstra <peterz@...radead.org>,
        Frederic Weisbecker <fweisbec@...il.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...nel.org>
Cc:     linux-kernel@...r.kernel.org, Scott Wood <swood@...hat.com>
Subject: [PATCH 1/4] tick/sched: Forward timer even in nohz mode

Currently when exiting nohz, the expiry will be forwarded as if we
had just run the timer.  If we re-enter nohz before this new expiry,
and exit after, this forwarding will happen again.  If this load pattern
recurs the tick can be indefinitely postponed.

To avoid this, use last_tick as-is rather than calling hrtimer_forward().
However, in some cases the tick *will* have just run (despite being
"stopped"), and leading to double timer execution.

To avoid that, forward the timer after every tick (regardless of nohz
status) and keep last_tick up-to-date.  During nohz, last_tick will
reflect what the expiry would have been if not in nohz mode.

Signed-off-by: Scott Wood <swood@...hat.com>
---
 kernel/time/tick-sched.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 8b192e67aabc..8936b604dd6c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -642,9 +642,6 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 	hrtimer_cancel(&ts->sched_timer);
 	hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
 
-	/* Forward the time to expire in the future */
-	hrtimer_forward(&ts->sched_timer, now, tick_period);
-
 	if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
 		hrtimer_start_expires(&ts->sched_timer,
 				      HRTIMER_MODE_ABS_PINNED_HARD);
@@ -1207,12 +1204,13 @@ static void tick_nohz_handler(struct clock_event_device *dev)
 
 	tick_sched_do_timer(ts, now);
 	tick_sched_handle(ts, regs);
+	hrtimer_forward(&ts->sched_timer, now, tick_period);
+	ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
 
 	/* No need to reprogram if we are running tickless  */
 	if (unlikely(ts->tick_stopped))
 		return;
 
-	hrtimer_forward(&ts->sched_timer, now, tick_period);
 	tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
 }
 
@@ -1311,12 +1309,13 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
 	else
 		ts->next_tick = 0;
 
+	hrtimer_forward(timer, now, tick_period);
+	ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
+
 	/* No need to reprogram if we are in idle or full dynticks mode */
 	if (unlikely(ts->tick_stopped))
 		return HRTIMER_NORESTART;
 
-	hrtimer_forward(timer, now, tick_period);
-
 	return HRTIMER_RESTART;
 }
 
-- 
1.8.3.1