linux-kernel - [RFC PATCH v3 6/6] Propagate negative bias

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: <f60a29ac1af5098e0d37d426aec27db05d5d43e1.1715082714.git.hongyan.xia2@arm.com>
Date: Tue,  7 May 2024 13:50:29 +0100
From: Hongyan Xia <hongyan.xia2@....com>
To: Ingo Molnar <mingo@...hat.com>,
	Peter Zijlstra <peterz@...radead.org>,
	Vincent Guittot <vincent.guittot@...aro.org>,
	Dietmar Eggemann <dietmar.eggemann@....com>,
	Juri Lelli <juri.lelli@...hat.com>,
	Steven Rostedt <rostedt@...dmis.org>,
	Ben Segall <bsegall@...gle.com>,
	Mel Gorman <mgorman@...e.de>,
	Daniel Bristot de Oliveira <bristot@...hat.com>,
	Valentin Schneider <vschneid@...hat.com>
Cc: Qais Yousef <qyousef@...alina.io>,
	Morten Rasmussen <morten.rasmussen@....com>,
	Lukasz Luba <lukasz.luba@....com>,
	Christian Loehle <christian.loehle@....com>,
	pierre.gondois@....com,
	linux-kernel@...r.kernel.org,
	Hongyan Xia <hongyan.xia2@....com>
Subject: [RFC PATCH v3 6/6] Propagate negative bias

Negative bias is interesting, because dequeuing such a task will
actually increase utilization.

Solve by applying PELT decay to negative biases as well. This in fact
can be implemented easily with some math tricks.

Signed-off-by: Hongyan Xia <hongyan.xia2@....com>
---
 kernel/sched/fair.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0177d7e8f364..7259a61e9ae5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4863,6 +4863,45 @@ static inline unsigned long task_util_est_uclamp(struct task_struct *p)
 {
 	return max(task_util_uclamp(p), _task_util_est_uclamp(p));
 }
+
+/*
+ * Negative biases are tricky. If we remove them right away then dequeuing a
+ * uclamp_max task has the interesting effect that dequeuing results in a higher
+ * rq utilization. Solve this by applying PELT decay to the bias itself.
+ *
+ * Keeping track of a PELT-decayed negative bias is extra overhead. However, we
+ * observe this interesting math property, where y is the decay factor and p is
+ * the number of periods elapsed:
+ *
+ *	util_new = util_old * y^p - neg_bias * y^p
+ *		 = (util_old - neg_bias) * y^p
+ *
+ * Therefore, we simply subtract the negative bias from util_avg the moment we
+ * dequeue, then the PELT signal itself is the total of util_avg and the decayed
+ * negative bias, and we no longer need to track the decayed bias separately.
+ */
+static void propagate_negative_bias(struct task_struct *p)
+{
+	if (task_util_bias(p) < 0 && !task_on_rq_migrating(p)) {
+		unsigned long neg_bias = -task_util_bias(p);
+		struct sched_entity *se = &p->se;
+		struct cfs_rq *cfs_rq;
+
+		p->se.avg.util_avg_bias = 0;
+
+		for_each_sched_entity(se) {
+			u32 divider, neg_sum;
+
+			cfs_rq = cfs_rq_of(se);
+			divider = get_pelt_divider(&cfs_rq->avg);
+			neg_sum = neg_bias * divider;
+			sub_positive(&se->avg.util_avg, neg_bias);
+			sub_positive(&se->avg.util_sum, neg_sum);
+			sub_positive(&cfs_rq->avg.util_avg, neg_bias);
+			sub_positive(&cfs_rq->avg.util_sum, neg_sum);
+		}
+	}
+}
 #else
 static inline long task_util_bias(struct task_struct *p)
 {
@@ -4883,6 +4922,10 @@ static inline unsigned long task_util_est_uclamp(struct task_struct *p)
 {
 	return task_util_est(p);
 }
+
+static void propagate_negative_bias(struct task_struct *p)
+{
+}
 #endif
 
 static inline void util_est_enqueue(struct cfs_rq *cfs_rq,
@@ -6844,6 +6887,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	/* At this point se is NULL and we are at root level*/
 	sub_nr_running(rq, 1);
 	util_bias_dequeue(&rq->cfs.avg, p);
+	propagate_negative_bias(p);
 	/* XXX: We should skip the update above and only do it once here. */
 	cpufreq_update_util(rq, 0);
 
-- 
2.34.1