From: Anna-Maria Behnsen <anna-maria@linutronix.de>
To: linux-kernel@vger.kernel.org
Cc: Peter Zijlstra <peterz@infradead.org>,
John Stultz <jstultz@google.com>,
Thomas Gleixner <tglx@linutronix.de>,
Eric Dumazet <edumazet@google.com>,
"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
Arjan van de Ven <arjan@infradead.org>,
"Paul E . McKenney" <paulmck@kernel.org>,
Frederic Weisbecker <fweisbec@gmail.com>,
Rik van Riel <riel@surriel.com>,
Anna-Maria Behnsen <anna-maria@linutronix.de>,
Richard Cochran <richardcochran@gmail.com>
Subject: [PATCH v5 18/18] timer: Always queue timers on the local CPU
Date: Wed, 1 Mar 2023 15:17:44 +0100 [thread overview]
Message-ID: <20230301141744.16063-19-anna-maria@linutronix.de> (raw)
In-Reply-To: <20230301141744.16063-1-anna-maria@linutronix.de>
The timer pull model is in place so we can remove the heuristics which try
to guess the best target CPU at enqueue/modification time.
All non pinned timers are queued on the local CPU in the seperate storage
and eventually pulled at expiry time to a remote CPU.
Originally-by: Richard Cochran (linutronix GmbH) <richardcochran@gmail.com>
Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
---
v5:
- Move WARN_ONCE() in add_timer_on() into a previous patch
- Fold "crystallball magic" related hunks into this patch
---
include/linux/timer.h | 5 ++---
kernel/time/timer.c | 42 ++++++++++++++++++++----------------------
2 files changed, 22 insertions(+), 25 deletions(-)
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 9162f275819a..aaedacac0b56 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -50,9 +50,8 @@ struct timer_list {
* workqueue locking issues. It's not meant for executing random crap
* with interrupts disabled. Abuse is monitored!
*
- * @TIMER_PINNED: A pinned timer will not be affected by any timer
- * placement heuristics (like, NOHZ) and will always expire on the CPU
- * on which the timer was enqueued.
+ * @TIMER_PINNED: A pinned timer will always expire on the CPU on which
+ * the timer was enqueued.
*
* Note: Because enqueuing of timers can migrate the timer from one
* CPU to another, pinned timers are not guaranteed to stay on the
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 01e97342ad0d..a441ec9dae39 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -593,10 +593,13 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
/*
* We might have to IPI the remote CPU if the base is idle and the
- * timer is not deferrable. If the other CPU is on the way to idle
- * then it can't set base->is_idle as we hold the base lock:
+ * timer is pinned. If it is a non pinned timer, it is only queued
+ * on the remote CPU, when timer was running during queueing. Then
+ * everything is handled by remote CPU anyway. If the other CPU is
+ * on the way to idle then it can't set base->is_idle as we hold
+ * the base lock:
*/
- if (base->is_idle)
+ if (base->is_idle && timer->flags & TIMER_PINNED)
wake_up_nohz_cpu(base->cpu);
}
@@ -944,17 +947,6 @@ static inline struct timer_base *get_timer_base(u32 tflags)
return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK);
}
-static inline struct timer_base *
-get_target_base(struct timer_base *base, unsigned tflags)
-{
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
- if (static_branch_likely(&timers_migration_enabled) &&
- !(tflags & TIMER_PINNED))
- return get_timer_cpu_base(tflags, get_nohz_timer_target());
-#endif
- return get_timer_this_cpu_base(tflags);
-}
-
static inline void forward_timer_base(struct timer_base *base)
{
unsigned long jnow = READ_ONCE(jiffies);
@@ -1106,7 +1098,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
if (!ret && (options & MOD_TIMER_PENDING_ONLY))
goto out_unlock;
- new_base = get_target_base(base, timer->flags);
+ new_base = get_timer_this_cpu_base(timer->flags);
if (base != new_base) {
/*
@@ -2127,8 +2119,14 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
*/
}
- /* We need to mark both bases in sync */
- base_local->is_idle = base_global->is_idle = is_idle;
+ /*
+ * base->is_idle information is required to wakeup a idle CPU when
+ * a new timer was enqueued. Only pinned timers could be enqueued
+ * remotely into a idle base. Therefore do maintain only
+ * base_local->is_idle information and ignore base_global->is_idle
+ * information.
+ */
+ base_local->is_idle = is_idle;
raw_spin_unlock(&base_global->lock);
raw_spin_unlock(&base_local->lock);
@@ -2158,13 +2156,13 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
void timer_clear_idle(void)
{
/*
- * We do this unlocked. The worst outcome is a remote enqueue sending
- * a pointless IPI, but taking the lock would just make the window for
- * sending the IPI a few instructions smaller for the cost of taking
- * the lock in the exit from idle path.
+ * We do this unlocked. The worst outcome is a remote pinned timer
+ * enqueue sending a pointless IPI, but taking the lock would just
+ * make the window for sending the IPI a few instructions smaller
+ * for the cost of taking the lock in the exit from idle
+ * path. Required for BASE_LOCAL only.
*/
__this_cpu_write(timer_bases[BASE_LOCAL].is_idle, false);
- __this_cpu_write(timer_bases[BASE_GLOBAL].is_idle, false);
/* Activate without holding the timer_base->lock */
tmigr_cpu_activate();
--
2.30.2
next prev parent reply other threads:[~2023-03-01 14:19 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-01 14:17 [PATCH v5 00/18] timer: Move from a push remote at enqueue to a pull at expiry model Anna-Maria Behnsen
2023-03-01 14:17 ` [PATCH v5 01/18] tick-sched: Warn when next tick seems to be in the past Anna-Maria Behnsen
2023-03-01 14:17 ` [PATCH v5 02/18] timer: Add comment to get_next_timer_interrupt() description Anna-Maria Behnsen
2023-04-11 9:36 ` Frederic Weisbecker
2023-04-11 16:10 ` Anna-Maria Behnsen
2023-04-12 11:29 ` Frederic Weisbecker
2023-03-01 14:17 ` [PATCH v5 03/18] timer: Move store of next event into __next_timer_interrupt() Anna-Maria Behnsen
2023-03-21 12:48 ` Peter Zijlstra
2023-04-12 11:32 ` Frederic Weisbecker
2023-03-01 14:17 ` [PATCH v5 04/18] timer: Split next timer interrupt logic Anna-Maria Behnsen
2023-03-01 14:17 ` [PATCH v5 05/18] timer: Rework idle logic Anna-Maria Behnsen
2023-03-01 14:17 ` [PATCH v5 06/18] add_timer_on(): Make sure callers have TIMER_PINNED flag Anna-Maria Behnsen
2023-03-01 14:17 ` [PATCH v5 07/18] timers: Ease code in run_local_timers() Anna-Maria Behnsen
2023-04-12 14:32 ` Frederic Weisbecker
2023-03-01 14:17 ` [PATCH v5 08/18] timers: Create helper function to forward timer base clk Anna-Maria Behnsen
2023-04-12 14:40 ` Frederic Weisbecker
2023-03-01 14:17 ` [PATCH v5 09/18] timer: Keep the pinned timers separate from the others Anna-Maria Behnsen
2023-03-01 14:17 ` [PATCH v5 10/18] timer: Retrieve next expiry of pinned/non-pinned timers seperately Anna-Maria Behnsen
2023-03-01 14:17 ` [PATCH v5 11/18] timer: Split out "get next timer interrupt" functionality Anna-Maria Behnsen
2023-03-09 16:30 ` Frederic Weisbecker
2023-03-09 17:45 ` Frederic Weisbecker
2023-03-21 14:30 ` Peter Zijlstra
2023-04-12 20:34 ` Frederic Weisbecker
2023-03-01 14:17 ` [PATCH v5 12/18] timer: Add get next timer interrupt functionality for remote CPUs Anna-Maria Behnsen
2023-03-01 14:17 ` [PATCH v5 13/18] timer: Restructure internal locking Anna-Maria Behnsen
2023-03-01 14:17 ` [PATCH v5 14/18] timer: Check if timers base is handled already Anna-Maria Behnsen
2023-03-21 14:43 ` Peter Zijlstra
2023-03-01 14:17 ` [PATCH v5 15/18] tick/sched: Split out jiffies update helper function Anna-Maria Behnsen
2023-03-01 14:17 ` [PATCH v5 16/18] timer: Implement the hierarchical pull model Anna-Maria Behnsen
2023-03-14 13:24 ` Frederic Weisbecker
2023-03-14 14:49 ` Anna-Maria Behnsen
2023-03-14 16:01 ` Frederic Weisbecker
2023-03-21 11:17 ` Frederic Weisbecker
2023-04-04 14:05 ` Anna-Maria Behnsen
2023-04-04 14:32 ` Frederic Weisbecker
2023-03-21 13:25 ` Frederic Weisbecker
2023-04-06 9:12 ` Anna-Maria Behnsen
2023-03-21 15:29 ` Peter Zijlstra
2023-03-21 15:34 ` Peter Zijlstra
2023-03-21 15:40 ` Peter Zijlstra
2023-03-23 9:22 ` Peter Zijlstra
2023-03-23 9:34 ` Peter Zijlstra
2023-03-23 9:47 ` Peter Zijlstra
2023-03-23 12:47 ` Peter Zijlstra
2023-03-23 14:24 ` Peter Zijlstra
2023-04-04 14:56 ` Anna-Maria Behnsen
2023-03-01 14:17 ` [PATCH v5 17/18] timer_migration: Add tracepoints Anna-Maria Behnsen
2023-03-01 14:17 ` Anna-Maria Behnsen [this message]
2023-03-21 12:46 ` [PATCH v5 00/18] timer: Move from a push remote at enqueue to a pull at expiry model Peter Zijlstra
2023-04-04 13:35 ` Anna-Maria Behnsen
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=20230301141744.16063-19-anna-maria@linutronix.de \
--to=anna-maria@linutronix.de \
--cc=arjan@infradead.org \
--cc=edumazet@google.com \
--cc=fweisbec@gmail.com \
--cc=jstultz@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=rafael.j.wysocki@intel.com \
--cc=richardcochran@gmail.com \
--cc=riel@surriel.com \
--cc=tglx@linutronix.de \
/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).