Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
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 <frederic@kernel.org>,
        Rik van Riel <riel@surriel.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Sebastian Siewior <bigeasy@linutronix.de>,
        Giovanni Gherdovich <ggherdovich@suse.cz>,
        Lukasz Luba <lukasz.luba@arm.com>,
        "Gautham R . Shenoy" <gautham.shenoy@amd.com>,
        Srinivas Pandruvada <srinivas.pandruvada@intel.com>,
        K Prateek Nayak <kprateek.nayak@amd.com>,
        Anna-Maria Behnsen <anna-maria@linutronix.de>,
        Richard Cochran <richardcochran@gmail.com>
Subject: [PATCH v8 25/25] timer: Always queue timers on the local CPU
Date:   Wed,  4 Oct 2023 14:34:54 +0200
Message-Id: <20231004123454.15691-26-anna-maria@linutronix.de>
In-Reply-To: <20231004123454.15691-1-anna-maria@linutronix.de>
References: <20231004123454.15691-1-anna-maria@linutronix.de>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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 separate 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>
---
v6:
 - Update TIMER_PINNED flag description.

v5:
 - Move WARN_ONCE() in add_timer_on() into a previous patch
 - Fold crystallball magic related hunks into this patch

v4: Update comment about TIMER_PINNED flag (heristic is removed)
---
 include/linux/timer.h | 14 ++++----------
 kernel/time/timer.c   | 42 ++++++++++++++++++++----------------------
 2 files changed, 24 insertions(+), 32 deletions(-)

diff --git a/include/linux/timer.h b/include/linux/timer.h
index 6f96661480dd..c39ae2ad0035 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -50,16 +50,10 @@ 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.
- *
- * Note: Because enqueuing of timers can migrate the timer from one
- * CPU to another, pinned timers are not guaranteed to stay on the
- * initialy selected CPU.  They move to the CPU on which the enqueue
- * function is invoked via mod_timer() or add_timer().  If the timer
- * should be placed on a particular CPU, then add_timer_on() has to be
- * used.
+ * @TIMER_PINNED: A pinned timer will always expire on the CPU on which the
+ * timer was enqueued. When a particular CPU is required, add_timer_on()
+ * has to be used. Enqueue via mod_timer() and add_timer() is always done
+ * on the local CPU.
  */
 #define TIMER_CPUMASK		0x0003FFFF
 #define TIMER_MIGRATING		0x00040000
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 331c59c0789a..feb915642457 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -590,10 +590,13 @@ 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);
 }
 
@@ -941,17 +944,6 @@ 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 basej)
 {
@@ -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) {
 		/*
@@ -2256,8 +2248,14 @@ u64 timer_set_idle(unsigned long basej, u64 basem, bool *idle)
 		 */
 	}
 
-	/* We need to mark both bases in sync */
-	base_local->is_idle = base_global->is_idle = *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 = *idle;
 
 	raw_spin_unlock(&base_global->lock);
 	raw_spin_unlock(&base_local->lock);
@@ -2273,13 +2271,13 @@ u64 timer_set_idle(unsigned long basej, u64 basem, bool *idle)
 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();
-- 
2.39.2