linux-kernel - [RFC PATCH v4 11/28] sched: Introduce per runqueue task LLC preference counter

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: <fc52347ecefb756cb3a9a7d90874e7c502fa55e0.1754712565.git.tim.c.chen@linux.intel.com>
Date: Sat,  9 Aug 2025 13:04:18 +0800
From: Chen Yu <yu.c.chen@...el.com>
To: Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...hat.com>,
	K Prateek Nayak <kprateek.nayak@....com>,
	"Gautham R . Shenoy" <gautham.shenoy@....com>
Cc: Vincent Guittot <vincent.guittot@...aro.org>,
	Juri Lelli <juri.lelli@...hat.com>,
	Dietmar Eggemann <dietmar.eggemann@....com>,
	Steven Rostedt <rostedt@...dmis.org>,
	Ben Segall <bsegall@...gle.com>,
	Mel Gorman <mgorman@...e.de>,
	Valentin Schneider <vschneid@...hat.com>,
	Libo Chen <libo.chen@...cle.com>,
	Madadi Vineeth Reddy <vineethr@...ux.ibm.com>,
	Hillf Danton <hdanton@...a.com>,
	Shrikanth Hegde <sshegde@...ux.ibm.com>,
	Jianyong Wu <jianyong.wu@...look.com>,
	Yangyu Chen <cyy@...self.name>,
	Tingyin Duan <tingyin.duan@...il.com>,
	Vern Hao <vernhao@...cent.com>,
	Len Brown <len.brown@...el.com>,
	Tim Chen <tim.c.chen@...ux.intel.com>,
	Aubrey Li <aubrey.li@...el.com>,
	Zhao Liu <zhao1.liu@...el.com>,
	Chen Yu <yu.chen.surf@...il.com>,
	Chen Yu <yu.c.chen@...el.com>,
	linux-kernel@...r.kernel.org
Subject: [RFC PATCH v4 11/28] sched: Introduce per runqueue task LLC preference counter

From: Tim Chen <tim.c.chen@...ux.intel.com>

Each runqueue is assigned a static array, where each element indicates
the number of tasks preferring a particular LLC mapped to the
array index.

For example, rq->nr_pref_llc[3] = 2 signifies that there are 2 tasks on
this runqueue which prefer to run within LLC3 (indexed from 0 to MAX_LLC
across the entire system). With this information, the load balancer can
make better decisions to select the busiest runqueue and migrate tasks
to their preferred LLC domains.

Note: The static array could be converted to an xarray in the future.

Signed-off-by: Tim Chen <tim.c.chen@...ux.intel.com>
---
 kernel/sched/fair.c  | 42 ++++++++++++++++++++++++++++++++++++++++--
 kernel/sched/sched.h |  1 +
 2 files changed, 41 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f964d5a44fcc..cfae71ee870b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1195,22 +1195,51 @@ static inline int llc_idx(int cpu)
 	return per_cpu(sd_llc_idx, cpu);
 }
 
+static inline int pref_llc_idx(struct task_struct *p)
+{
+	return llc_idx(p->preferred_llc);
+}
+
 static void account_llc_enqueue(struct rq *rq, struct task_struct *p)
 {
+	int pref_llc;
+
 	if (!sched_feat(SCHED_CACHE))
 		return;
 
 	rq->nr_llc_running += (p->preferred_llc != -1);
 	rq->nr_pref_llc_running += (p->preferred_llc == task_llc(p));
+
+	if (p->preferred_llc < 0)
+		return;
+
+	pref_llc = pref_llc_idx(p);
+	if (pref_llc < 0)
+		return;
+
+	++rq->nr_pref_llc[pref_llc];
 }
 
 static void account_llc_dequeue(struct rq *rq, struct task_struct *p)
 {
+	int pref_llc;
+
 	if (!sched_feat(SCHED_CACHE))
 		return;
 
 	rq->nr_llc_running -= (p->preferred_llc != -1);
 	rq->nr_pref_llc_running -= (p->preferred_llc == task_llc(p));
+
+	if (p->preferred_llc < 0)
+		return;
+
+	pref_llc = pref_llc_idx(p);
+	if (pref_llc < 0)
+		return;
+
+	/* avoid negative counter */
+	if (rq->nr_pref_llc[pref_llc] > 0)
+		--rq->nr_pref_llc[pref_llc];
 }
 
 void mm_init_sched(struct mm_struct *mm, struct mm_sched __percpu *_pcpu_sched)
@@ -1279,6 +1308,8 @@ static unsigned long __no_profile fraction_mm_sched(struct rq *rq, struct mm_sch
 	return div64_u64(NICE_0_LOAD * pcpu_sched->runtime, rq->cpu_runtime + 1);
 }
 
+static unsigned int task_running_on_cpu(int cpu, struct task_struct *p);
+
 static inline
 void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec)
 {
@@ -1321,7 +1352,9 @@ void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec)
 	if (mm->mm_sched_cpu != -1)
 		mm_sched_llc = per_cpu(sd_llc_id, mm->mm_sched_cpu);
 
-	if (p->preferred_llc != mm_sched_llc) {
+	/* task not on rq accounted later in account_entity_enqueue() */
+	if (task_running_on_cpu(rq->cpu, p) &&
+	    p->preferred_llc != mm_sched_llc) {
 		account_llc_dequeue(rq, p);
 		p->preferred_llc = mm_sched_llc;
 		account_llc_enqueue(rq, p);
@@ -1431,11 +1464,16 @@ void init_sched_mm(struct task_struct *p)
 
 void reset_llc_stats(struct rq *rq)
 {
+	int i;
+
 	if (!sched_feat(SCHED_CACHE))
 		return;
 
-	if (rq->nr_llc_running)
+	if (rq->nr_llc_running) {
+		for (i = 0; i < MAX_LLC; ++i)
+			rq->nr_pref_llc[i] = 0;
 		rq->nr_llc_running = 0;
+	}
 
 	rq->nr_pref_llc_running = 0;
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 8026e2c66e9f..4464b92767ad 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1109,6 +1109,7 @@ struct rq {
 #ifdef CONFIG_SCHED_CACHE
 	unsigned int		nr_pref_llc_running;
 	unsigned int		nr_llc_running;
+	unsigned int		nr_pref_llc[MAX_LLC];
 #endif
 #ifdef CONFIG_NO_HZ_COMMON
 #ifdef CONFIG_SMP
-- 
2.25.1