linux-kernel - [PATCH v1] cpuidle: governors: teo: Special-case nohz

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] [day] [month] [year] [list]

Message-ID: <5939372.DvuYhMxLoT@rafael.j.wysocki>
Date: Thu, 28 Aug 2025 22:16:20 +0200
From: "Rafael J. Wysocki" <rafael@...nel.org>
To: Linux PM <linux-pm@...r.kernel.org>
Cc: Frederic Weisbecker <frederic@...nel.org>,
 LKML <linux-kernel@...r.kernel.org>, Peter Zijlstra <peterz@...radead.org>,
 Christian Loehle <christian.loehle@....com>
Subject: [PATCH v1] cpuidle: governors: teo: Special-case nohz_full CPUs

From: Rafael J. Wysocki <rafael.j.wysocki@...el.com>

This change follows an analogous modification of the menu governor [1].

Namely, when the governor runs on a nohz_full CPU and there are no user
space timers in the workload on that CPU, it ends up selecting idle
states with target residency values above TICK_NSEC, or the deepest
enabled idle state in the absence of any of those, all the time due to
a tick_nohz_tick_stopped() check designed for running on CPUs where the
tick is not permanently disabled.  In that case, the fact that the tick
has been stopped means that the CPU was expected to be idle sufficiently
long previously, so it is not unreasonable to expect it to be idle
sufficiently long again, but this inference does not apply to nohz_full
CPUs.

In some cases, latency in the workload grows undesirably as a result of
selecting overly deep idle states, and the workload may also consume
more energy than necessary if the CPU does not spend enough time in the
selected deep idle state.

Address this by amending the tick_nohz_tick_stopped() check in question
with a tick_nohz_full_cpu() one to avoid effectively ignoring all
shallow idle states on nohz_full CPUs.  While doing so introduces a risk
of getting stuck in a shallow idle state for a long time, that only
affects energy efficiently, but the current behavior potentially hurts
both energy efficiency and performance that is arguably the priority for
nohz_full CPUs.

While at it, add a comment explaining the logic in teo_state_ok().

Link: https://lore.kernel.org/linux-pm/2244365.irdbgypaU6@rafael.j.wysocki/ [1]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@...el.com>
---
 drivers/cpuidle/governors/teo.c |   18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

--- a/drivers/cpuidle/governors/teo.c
+++ b/drivers/cpuidle/governors/teo.c
@@ -227,9 +227,17 @@
 	cpu_data->total += PULSE;
 }

-static bool teo_state_ok(int i, struct cpuidle_driver *drv)
+static bool teo_state_ok(int i, struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
-	return !tick_nohz_tick_stopped() ||
+	/*
+	 * If the scheduler tick has been stopped already, avoid selecting idle
+	 * states with target residency below the tick period length under the
+	 * assumption that the CPU is likely to be idle sufficiently long for
+	 * the tick to be stopped again (or the tick would not have been
+	 * stopped previously in the first place).  However, do not do that on
+	 * nohz_full CPUs where the above assumption does not hold.
+	 */
+	return !tick_nohz_tick_stopped() || tick_nohz_full_cpu(dev->cpu) ||
 		drv->states[i].target_residency_ns >= TICK_NSEC;
 }

@@ -379,7 +387,7 @@
 				 * shallow or disabled, in which case take the
 				 * first enabled state that is deep enough.
 				 */
-				if (teo_state_ok(i, drv) &&
+				if (teo_state_ok(i, drv, dev) &&
 				    !dev->states_usage[i].disable) {
 					idx = i;
 					break;
@@ -391,7 +399,7 @@
 			if (dev->states_usage[i].disable)
 				continue;

-			if (teo_state_ok(i, drv)) {
+			if (teo_state_ok(i, drv, dev)) {
 				/*
 				 * The current state is deep enough, but still
 				 * there may be a better one.
@@ -460,7 +468,7 @@
 	 */
 	if (drv->states[idx].target_residency_ns > duration_ns) {
 		i = teo_find_shallower_state(drv, dev, idx, duration_ns, false);
-		if (teo_state_ok(i, drv))
+		if (teo_state_ok(i, drv, dev))
 			idx = i;
 	}