From 500f8f9bced86f0c0f2482773bd64a1b7ec9c4e1 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Sun, 25 Feb 2024 23:55:07 +0100
Subject: [PATCH] tick: Assume timekeeping is correctly handed over upon last
offline idle call
The timekeeping duty is handed over from the outgoing CPU on stop
machine, then the oneshot tick is stopped right after. Therefore it's
guaranteed that the current CPU isn't the timekeeper upon its last call
to idle.
Besides, calling tick_nohz_idle_stop_tick() while the dying CPU goes
into idle suggests that the tick is going to be stopped while it is
actually stopped already from the appropriate CPU hotplug state.
Remove the confusing call and the obsolete case handling and convert it
to a sanity check that verifies the above assumption.
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20240225225508.11587-16-frederic@kernel.org
---
include/linux/tick.h | 2 ++
kernel/cpu.c | 1 +
kernel/sched/idle.c | 1 -
kernel/time/tick-common.c | 4 ++++
kernel/time/tick-sched.c | 13 +------------
5 files changed, 8 insertions(+), 13 deletions(-)
diff --git a/include/linux/tick.h b/include/linux/tick.h
index c7840ae8ebafb..44fddfa93e18c 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -29,8 +29,10 @@ static inline void tick_cleanup_dead_cpu(int cpu) { }
#if defined(CONFIG_GENERIC_CLOCKEVENTS) && defined(CONFIG_HOTPLUG_CPU)
extern int tick_cpu_dying(unsigned int cpu);
+extern void tick_assert_timekeeping_handover(void);
#else
#define tick_cpu_dying NULL
+static inline void tick_assert_timekeeping_handover(void) { }
#endif
#if defined(CONFIG_GENERIC_CLOCKEVENTS) && defined(CONFIG_SUSPEND)
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 5a8ad4f5ccf33..7e84a7b0675ef 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1399,6 +1399,7 @@ void cpuhp_report_idle_dead(void)
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
BUG_ON(st->state != CPUHP_AP_OFFLINE);
+ tick_assert_timekeeping_handover();
rcutree_report_cpu_dead();
st->state = CPUHP_AP_IDLE_DEAD;
/*
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 31231925f1ece..b15d40cad7ea4 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -291,7 +291,6 @@ static void do_idle(void)
local_irq_disable();
if (cpu_is_offline(cpu)) {
- tick_nohz_idle_stop_tick();
cpuhp_report_idle_dead();
arch_cpu_idle_dead();
}
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 9cd09eea06d6e..fb0fdec8719a1 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -396,6 +396,10 @@ int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control);
#ifdef CONFIG_HOTPLUG_CPU
+void tick_assert_timekeeping_handover(void)
+{
+ WARN_ON_ONCE(tick_do_timer_cpu == smp_processor_id());
+}
/*
* Stop the tick and transfer the timekeeping job away from a dying cpu.
*/
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 89d16b8ea2c4f..269e21590df53 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1160,18 +1160,7 @@ static bool report_idle_softirq(void)
static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
{
- /*
- * If this CPU is offline and it is the one which updates
- * jiffies, then give up the assignment and let it be taken by
- * the CPU which runs the tick timer next. If we don't drop
- * this here, the jiffies might be stale and do_timer() never
- * gets invoked.
- */
- if (unlikely(!cpu_online(cpu))) {
- if (cpu == tick_do_timer_cpu)
- tick_do_timer_cpu = TICK_DO_TIMER_NONE;
- return false;
- }
+ WARN_ON_ONCE(cpu_is_offline(cpu));
if (unlikely(!tick_sched_flag_test(ts, TS_FLAG_NOHZ)))
return false;
--
GitLab