linux-kernel - [PATCH v5 18/18] timer: Always queue timers on the local CPU

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-prev] [thread-next>] [day] [month] [year] [list]
Date:   Wed,  1 Mar 2023 15:17:44 +0100
From:   Anna-Maria Behnsen <anna-maria@...utronix.de>
To:     linux-kernel@...r.kernel.org
Cc:     Peter Zijlstra <peterz@...radead.org>,
        John Stultz <jstultz@...gle.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Eric Dumazet <edumazet@...gle.com>,
        "Rafael J . Wysocki" <rafael.j.wysocki@...el.com>,
        Arjan van de Ven <arjan@...radead.org>,
        "Paul E . McKenney" <paulmck@...nel.org>,
        Frederic Weisbecker <fweisbec@...il.com>,
        Rik van Riel <riel@...riel.com>,
        Anna-Maria Behnsen <anna-maria@...utronix.de>,
        Richard Cochran <richardcochran@...il.com>
Subject: [PATCH v5 18/18] timer: Always queue timers on the local CPU

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@...il.com>
Signed-off-by: Anna-Maria Behnsen <anna-maria@...utronix.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