public inbox for rcu@vger.kernel.org
 help / color / mirror / Atom feed
From: Qiliang Yuan <realwujing@gmail.com>
To: Ingo Molnar <mingo@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	 Juri Lelli <juri.lelli@redhat.com>,
	 Vincent Guittot <vincent.guittot@linaro.org>,
	 Dietmar Eggemann <dietmar.eggemann@arm.com>,
	 Steven Rostedt <rostedt@goodmis.org>,
	Ben Segall <bsegall@google.com>,  Mel Gorman <mgorman@suse.de>,
	Valentin Schneider <vschneid@redhat.com>,
	 Thomas Gleixner <tglx@kernel.org>,
	"Paul E. McKenney" <paulmck@kernel.org>,
	 Frederic Weisbecker <frederic@kernel.org>,
	 Neeraj Upadhyay <neeraj.upadhyay@kernel.org>,
	 Joel Fernandes <joelagnelf@nvidia.com>,
	 Josh Triplett <josh@joshtriplett.org>,
	Boqun Feng <boqun.feng@gmail.com>,
	 Uladzislau Rezki <urezki@gmail.com>,
	 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	 Lai Jiangshan <jiangshanlai@gmail.com>,
	Zqiang <qiang.zhang@linux.dev>,  Tejun Heo <tj@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	 Vlastimil Babka <vbabka@suse.cz>,
	Suren Baghdasaryan <surenb@google.com>,
	 Michal Hocko <mhocko@suse.com>,
	Brendan Jackman <jackmanb@google.com>,
	 Johannes Weiner <hannes@cmpxchg.org>, Zi Yan <ziy@nvidia.com>,
	 Anna-Maria Behnsen <anna-maria@linutronix.de>,
	 Ingo Molnar <mingo@kernel.org>, Shuah Khan <shuah@kernel.org>
Cc: linux-kernel@vger.kernel.org, rcu@vger.kernel.org,
	linux-mm@kvack.org,  linux-kselftest@vger.kernel.org,
	Qiliang Yuan <realwujing@gmail.com>
Subject: [PATCH 10/15] tick/nohz: Transition to dynamic full dynticks state management
Date: Wed, 25 Mar 2026 17:09:41 +0800	[thread overview]
Message-ID: <20260325-dhei-v12-final-v1-10-919cca23cadf@gmail.com> (raw)
In-Reply-To: <20260325-dhei-v12-final-v1-0-919cca23cadf@gmail.com>

Context:
Full dynticks (NOHZ_FULL) is typically a static configuration determined
at boot time. DHEI extends this to support runtime activation.

Problem:
Switching to NOHZ_FULL at runtime requires careful synchronization
of context tracking and housekeeping states. Re-invoking setup logic
multiple times could lead to inconsistencies or warnings, and RCU
dependency checks often prevented tick suppression in "Zero-Conf" setups.

Solution:
- Replaced the static tick_nohz_full_enabled() checks with a dynamic
  tick_nohz_full_running state variable.
- Refactored tick_nohz_full_setup to be safe for runtime invocation,
  adding guards against re-initialization and ensuring IRQ work
  interrupt support.
- Implemented boot-time pre-activation of context tracking (shadow
  init) for all possible CPUs to avoid instruction flow issues during
  dynamic transitions.
- Restored standard rcu_needs_cpu() checks now that RCU supports
  native dynamic NOCB mode switching.

This provides the core state machine for reliable, on-demand tick
suppression and high-performance isolation.
---
 kernel/time/tick-sched.c | 130 ++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 105 insertions(+), 25 deletions(-)

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 2f8a7923fa279..dee42cea259a9 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -27,6 +27,7 @@
 #include <linux/posix-timers.h>
 #include <linux/context_tracking.h>
 #include <linux/mm.h>
+#include <linux/sched/isolation.h>
 
 #include <asm/irq_regs.h>
 
@@ -621,13 +622,25 @@ void __tick_nohz_task_switch(void)
 /* Get the boot-time nohz CPU list from the kernel parameters. */
 void __init tick_nohz_full_setup(cpumask_var_t cpumask)
 {
-	alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
+	if (!tick_nohz_full_mask) {
+		if (!slab_is_available())
+			alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
+		else
+			zalloc_cpumask_var(&tick_nohz_full_mask, GFP_KERNEL);
+	}
 	cpumask_copy(tick_nohz_full_mask, cpumask);
 	tick_nohz_full_running = true;
 }
 
 bool tick_nohz_cpu_hotpluggable(unsigned int cpu)
 {
+	/*
+	 * Allow all CPUs to go down during shutdown/reboot to avoid
+	 * interfering with the final power-off sequence.
+	 */
+	if (system_state > SYSTEM_RUNNING)
+		return true;
+
 	/*
 	 * The 'tick_do_timer_cpu' CPU handles housekeeping duty (unbound
 	 * timers, workqueues, timekeeping, ...) on behalf of full dynticks
@@ -643,45 +656,112 @@ static int tick_nohz_cpu_down(unsigned int cpu)
 	return tick_nohz_cpu_hotpluggable(cpu) ? 0 : -EBUSY;
 }
 
+static int tick_nohz_housekeeping_reconfigure(struct notifier_block *nb,
+					     unsigned long action, void *data)
+{
+	struct housekeeping_update *upd = data;
+	int cpu;
+
+	if (action == HK_UPDATE_MASK && upd->type == HK_TYPE_TICK) {
+		cpumask_var_t non_housekeeping_mask;
+
+		if (!alloc_cpumask_var(&non_housekeeping_mask, GFP_KERNEL))
+			return NOTIFY_BAD;
+
+		cpumask_andnot(non_housekeeping_mask, cpu_possible_mask, upd->new_mask);
+
+		if (!tick_nohz_full_mask) {
+			if (!zalloc_cpumask_var(&tick_nohz_full_mask, GFP_KERNEL)) {
+				free_cpumask_var(non_housekeeping_mask);
+				return NOTIFY_BAD;
+			}
+		}
+
+		/* Kick all CPUs to re-evaluate tick dependency before change */
+		for_each_online_cpu(cpu)
+			tick_nohz_full_kick_cpu(cpu);
+
+		cpumask_copy(tick_nohz_full_mask, non_housekeeping_mask);
+		tick_nohz_full_running = !cpumask_empty(tick_nohz_full_mask);
+
+		/*
+		 * If nohz_full is running, the timer duty must be on a housekeeper.
+		 * If the current timer CPU is not a housekeeper, or no duty is assigned,
+		 * pick the first housekeeper and assign it.
+		 */
+		if (tick_nohz_full_running) {
+			int timer_cpu = READ_ONCE(tick_do_timer_cpu);
+			if (timer_cpu == TICK_DO_TIMER_NONE ||
+			    !cpumask_test_cpu(timer_cpu, upd->new_mask)) {
+				int next_timer = cpumask_first(upd->new_mask);
+				if (next_timer < nr_cpu_ids)
+					WRITE_ONCE(tick_do_timer_cpu, next_timer);
+			}
+		}
+
+		/* Kick all CPUs again to apply new nohz full state */
+		for_each_online_cpu(cpu)
+			tick_nohz_full_kick_cpu(cpu);
+
+		free_cpumask_var(non_housekeeping_mask);
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block tick_nohz_housekeeping_nb = {
+	.notifier_call = tick_nohz_housekeeping_reconfigure,
+};
+
 void __init tick_nohz_init(void)
 {
 	int cpu, ret;
 
-	if (!tick_nohz_full_running)
-		return;
-
-	/*
-	 * Full dynticks uses IRQ work to drive the tick rescheduling on safe
-	 * locking contexts. But then we need IRQ work to raise its own
-	 * interrupts to avoid circular dependency on the tick.
-	 */
-	if (!arch_irq_work_has_interrupt()) {
-		pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support IRQ work self-IPIs\n");
-		cpumask_clear(tick_nohz_full_mask);
-		tick_nohz_full_running = false;
-		return;
+	if (!tick_nohz_full_mask) {
+		if (!slab_is_available())
+			alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
+		else
+			zalloc_cpumask_var(&tick_nohz_full_mask, GFP_KERNEL);
 	}
 
-	if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) &&
-			!IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) {
-		cpu = smp_processor_id();
+	housekeeping_register_notifier(&tick_nohz_housekeeping_nb);
 
-		if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
-			pr_warn("NO_HZ: Clearing %d from nohz_full range "
-				"for timekeeping\n", cpu);
-			cpumask_clear_cpu(cpu, tick_nohz_full_mask);
+	if (tick_nohz_full_running) {
+		/*
+		 * Full dynticks uses IRQ work to drive the tick rescheduling on safe
+		 * locking contexts. But then we need IRQ work to raise its own
+		 * interrupts to avoid circular dependency on the tick.
+		 */
+		if (!arch_irq_work_has_interrupt()) {
+			pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support IRQ work self-IPIs\n");
+			cpumask_clear(tick_nohz_full_mask);
+			tick_nohz_full_running = false;
+			goto out;
 		}
+
+		if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) &&
+				!IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) {
+			cpu = smp_processor_id();
+
+			if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
+				pr_warn("NO_HZ: Clearing %d from nohz_full range "
+					"for timekeeping\n", cpu);
+				cpumask_clear_cpu(cpu, tick_nohz_full_mask);
+			}
+		}
+
+		pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n",
+			cpumask_pr_args(tick_nohz_full_mask));
 	}
 
-	for_each_cpu(cpu, tick_nohz_full_mask)
+out:
+	for_each_possible_cpu(cpu)
 		ct_cpu_track_user(cpu);
 
 	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
 					"kernel/nohz:predown", NULL,
 					tick_nohz_cpu_down);
 	WARN_ON(ret < 0);
-	pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n",
-		cpumask_pr_args(tick_nohz_full_mask));
 }
 #endif /* #ifdef CONFIG_NO_HZ_FULL */
 
@@ -1200,7 +1280,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 	if (unlikely(report_idle_softirq()))
 		return false;
 
-	if (tick_nohz_full_enabled()) {
+	if (tick_nohz_full_running) {
 		int tick_cpu = READ_ONCE(tick_do_timer_cpu);
 
 		/*

-- 
2.43.0


  parent reply	other threads:[~2026-03-25  9:10 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-25  9:09 [PATCH 00/15] Implementation of Dynamic Housekeeping & Enhanced Isolation (DHEI) Qiliang Yuan
2026-03-25  9:09 ` [PATCH 01/15] sched/isolation: Support dynamic allocation for housekeeping masks Qiliang Yuan
2026-03-25 13:57   ` Peter Zijlstra
2026-03-25  9:09 ` [PATCH 02/15] sched/isolation: Introduce housekeeping notifier infrastructure Qiliang Yuan
2026-03-25 13:58   ` Peter Zijlstra
2026-03-25  9:09 ` [PATCH 03/15] sched/isolation: Separate housekeeping types in enum hk_type Qiliang Yuan
2026-03-25 13:59   ` Peter Zijlstra
2026-03-25  9:09 ` [PATCH 04/15] genirq: Support dynamic migration for managed interrupts Qiliang Yuan
2026-03-25  9:09 ` [PATCH 05/15] rcu: Support runtime NOCB initialization and dynamic offloading Qiliang Yuan
2026-03-25  9:09 ` [PATCH 06/15] sched/core: Dynamically update scheduler domain housekeeping mask Qiliang Yuan
2026-03-25 14:00   ` Peter Zijlstra
2026-03-25  9:09 ` [PATCH 07/15] watchdog: Allow runtime toggle of lockup detector affinity Qiliang Yuan
2026-03-25 14:03   ` Peter Zijlstra
2026-03-25  9:09 ` [PATCH 08/15] workqueue: Support dynamic housekeeping mask updates Qiliang Yuan
2026-03-25  9:09 ` [PATCH 09/15] mm/compaction: Support dynamic housekeeping mask updates for kcompactd Qiliang Yuan
2026-03-25  9:09 ` Qiliang Yuan [this message]
2026-03-25  9:09 ` [PATCH 11/15] sched/isolation: Implement SMT-aware isolation and safety guards Qiliang Yuan
2026-03-25  9:09 ` [PATCH 12/15] sched/isolation: Bridge boot-time parameters with dynamic isolation Qiliang Yuan
2026-03-25  9:09 ` [PATCH 13/15] sched/isolation: Implement sysfs interface for dynamic housekeeping Qiliang Yuan
2026-03-25 14:04   ` Peter Zijlstra
2026-03-25  9:09 ` [PATCH 14/15] Documentation: isolation: Document DHEI sysfs interfaces Qiliang Yuan
2026-03-25  9:09 ` [PATCH 15/15] selftests: dhei: Add functional tests for dynamic housekeeping Qiliang Yuan
2026-03-25 16:02 ` [PATCH 00/15] Implementation of Dynamic Housekeeping & Enhanced Isolation (DHEI) Tejun Heo

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=20260325-dhei-v12-final-v1-10-919cca23cadf@gmail.com \
    --to=realwujing@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=anna-maria@linutronix.de \
    --cc=boqun.feng@gmail.com \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=frederic@kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=jackmanb@google.com \
    --cc=jiangshanlai@gmail.com \
    --cc=joelagnelf@nvidia.com \
    --cc=josh@joshtriplett.org \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.com \
    --cc=mingo@kernel.org \
    --cc=mingo@redhat.com \
    --cc=neeraj.upadhyay@kernel.org \
    --cc=paulmck@kernel.org \
    --cc=peterz@infradead.org \
    --cc=qiang.zhang@linux.dev \
    --cc=rcu@vger.kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=shuah@kernel.org \
    --cc=surenb@google.com \
    --cc=tglx@kernel.org \
    --cc=tj@kernel.org \
    --cc=urezki@gmail.com \
    --cc=vbabka@suse.cz \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.com \
    --cc=ziy@nvidia.com \
    /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