linux-kernel - [PATCH v2 4/4] cpuidle: governors: teo: Decay metrics below DECAY

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]

Message-ID: <2819353.mvXUDI8C0e@rafael.j.wysocki>
Date: Wed, 12 Nov 2025 19:03:08 +0100
From: "Rafael J. Wysocki" <rafael@...nel.org>
To: Linux PM <linux-pm@...r.kernel.org>,
 Christian Loehle <christian.loehle@....com>
Cc: LKML <linux-kernel@...r.kernel.org>, Reka Norman <rekanorman@...omium.org>
Subject:
 [PATCH v2 4/4] cpuidle: governors: teo: Decay metrics below DECAY_SHIFT
 threshold

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

If a given governor metric falls below a certain value (8 for
DECAY_SHIFT equal to 3), it will not decay any more due to the
simplistic decay implementation.  This may in some cases lead to
subtle inconsistencies in the governor behavior, so change the
decay implementation to take it into account and set the metric
at hand to 0 in that case.

Suggested-by: Christian Loehle <christian.loehle@....com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@...el.com>
---

v1 -> v2:
   * Ensure that cpu_data->total is always the sum of the intercepts and hits
     metrics for all of the idle states (Christian).

---
 drivers/cpuidle/governors/teo.c |   26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

--- a/drivers/cpuidle/governors/teo.c
+++ b/drivers/cpuidle/governors/teo.c
@@ -148,6 +148,16 @@ struct teo_cpu {
 
 static DEFINE_PER_CPU(struct teo_cpu, teo_cpus);
 
+static void teo_decay(unsigned int *metric)
+{
+	unsigned int delta = *metric >> DECAY_SHIFT;
+
+	if (delta)
+		*metric -= delta;
+	else
+		*metric = 0;
+}
+
 /**
  * teo_update - Update CPU metrics after wakeup.
  * @drv: cpuidle driver containing state data.
@@ -158,8 +168,9 @@ static void teo_update(struct cpuidle_dr
 	struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
 	int i, idx_timer = 0, idx_duration = 0;
 	s64 target_residency_ns, measured_ns;
+	unsigned int total = 0;
 
-	cpu_data->short_idles -= cpu_data->short_idles >> DECAY_SHIFT;
+	teo_decay(&cpu_data->short_idles);
 
 	if (cpu_data->artificial_wakeup) {
 		/*
@@ -195,8 +206,10 @@ static void teo_update(struct cpuidle_dr
 	for (i = 0; i < drv->state_count; i++) {
 		struct teo_bin *bin = &cpu_data->state_bins[i];
 
-		bin->hits -= bin->hits >> DECAY_SHIFT;
-		bin->intercepts -= bin->intercepts >> DECAY_SHIFT;
+		teo_decay(&bin->hits);
+		total += bin->hits;
+		teo_decay(&bin->intercepts);
+		total += bin->intercepts;
 
 		target_residency_ns = drv->states[i].target_residency_ns;
 
@@ -207,7 +220,9 @@ static void teo_update(struct cpuidle_dr
 		}
 	}
 
-	cpu_data->tick_intercepts -= cpu_data->tick_intercepts >> DECAY_SHIFT;
+	cpu_data->total = total + PULSE;
+
+	teo_decay(&cpu_data->tick_intercepts);
 	/*
 	 * If the measured idle duration falls into the same bin as the sleep
 	 * length, this is a "hit", so update the "hits" metric for that bin.
@@ -221,9 +236,6 @@ static void teo_update(struct cpuidle_dr
 		if (TICK_NSEC <= measured_ns)
 			cpu_data->tick_intercepts += PULSE;
 	}
-
-	cpu_data->total -= cpu_data->total >> DECAY_SHIFT;
-	cpu_data->total += PULSE;
 }
 
 static bool teo_state_ok(int i, struct cpuidle_driver *drv)