linux-kernel - [PATCH v2 7/8] sched/uclamp: 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] [day] [month] [year] [list]

Message-Id: <53749ecebbed9ef59f6f0fea9c8a8daec0733d68.1741091349.git.hongyan.xia2@arm.com>
Date: Tue,  4 Mar 2025 14:23:14 +0000
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>,
	Valentin Schneider <vschneid@...hat.com>
Cc: Morten Rasmussen <morten.rasmussen@....com>,
	Lukasz Luba <lukasz.luba@....com>,
	Christian Loehle <christian.loehle@....com>,
	Pierre Gondois <pierre.gondois@....com>,
	linux-kernel@...r.kernel.org
Subject: [PATCH v2 7/8] sched/uclamp: 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  | 46 +++++++++++++++++++++++++++++++++++++++++++-
 kernel/sched/sched.h |  4 ++++
 2 files changed, 49 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 68e7b1ac7a57..944953b90297 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4886,6 +4886,48 @@ static inline unsigned long root_cfs_util_uclamp(struct rq *rq)
 
 	return max(ret, 0L);
 }
+
+/*
+ * 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;
+
+		p->se.avg.util_avg_bias = 0;
+
+		for_each_sched_entity(se) {
+			struct sched_avg *sa = &se->avg;
+			u32 divider = get_pelt_divider(sa);
+
+			sub_positive(&sa->util_avg, neg_bias);
+			sub_positive(&sa->util_sum, neg_bias * divider);
+			sa->util_sum = max_t(u32, sa->util_sum,
+					     sa->util_avg * PELT_MIN_DIVIDER);
+			sa = &cfs_rq_of(se)->avg;
+			divider = get_pelt_divider(sa);
+			sub_positive(&sa->util_avg, neg_bias);
+			sub_positive(&sa->util_sum, neg_bias * divider);
+			sa->util_sum = max_t(u32, sa->util_sum,
+					     sa->util_avg * PELT_MIN_DIVIDER);
+		}
+	}
+}
 #else
 static inline long task_util_bias(struct task_struct *p)
 {
@@ -7114,8 +7156,10 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 	}
 
 	sub_nr_running(rq, h_nr_queued);
-	if (p)
+	if (p) {
 		util_bias_dequeue(rq, p);
+		propagate_negative_bias(p);
+	}
 
 	if (rq_h_nr_queued && !rq->cfs.h_nr_queued)
 		dl_server_stop(&rq->fair_server);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f4a82e6cc029..654eede62979 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3431,6 +3431,10 @@ static inline void util_bias_dequeue(struct rq *rq, struct task_struct *p)
 {
 }
 
+static inline void propagate_negative_bias(struct task_struct *p)
+{
+}
+
 #endif /* !CONFIG_UCLAMP_TASK */
 
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
-- 
2.34.1