linux-kernel - [RFC patch v3 19/20] sched: Introduce SCHED_CACHE

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: <ac0e58b587dcd1e3ebe7a7a97973c5763d02a5f8.1750268218.git.tim.c.chen@linux.intel.com>
Date: Wed, 18 Jun 2025 11:28:07 -0700
From: Tim Chen <tim.c.chen@...ux.intel.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: Tim Chen <tim.c.chen@...ux.intel.com>,
	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>,
	Tim Chen <tim.c.chen@...el.com>,
	Vincent Guittot <vincent.guittot@...aro.org>,
	Libo Chen <libo.chen@...cle.com>,
	Abel Wu <wuyun.abel@...edance.com>,
	Madadi Vineeth Reddy <vineethr@...ux.ibm.com>,
	Hillf Danton <hdanton@...a.com>,
	Len Brown <len.brown@...el.com>,
	linux-kernel@...r.kernel.org,
	Chen Yu <yu.c.chen@...el.com>
Subject: [RFC patch v3 19/20] sched: Introduce SCHED_CACHE_LB to control cache aware load balance

Introduce the SCHED_CACHE_LB sched feature to enable or disable
cache aware load balance in the schduler.

Co-developed-by: Chen Yu <yu.c.chen@...el.com>
Signed-off-by: Tim Chen <tim.c.chen@...ux.intel.com>
---
 kernel/sched/fair.c     | 18 ++++++++++--------
 kernel/sched/features.h |  1 +
 2 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e342524481ed..af742601f2d7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9982,7 +9982,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 		return 1;
 
 #ifdef CONFIG_SCHED_CACHE
-	if (sched_feat(SCHED_CACHE) &&
+	if (sched_feat(SCHED_CACHE) && sched_feat(SCHED_CACHE_LB) &&
 	    get_migrate_hint(env->src_cpu, env->dst_cpu, p) == mig_forbid)
 		return 0;
 #endif
@@ -10068,7 +10068,7 @@ static struct list_head
 	LIST_HEAD(no_pref_llc);
 	LIST_HEAD(pref_other_llc);
 
-	if (!sched_feat(SCHED_CACHE))
+	if (!sched_feat(SCHED_CACHE) || !sched_feat(SCHED_CACHE_LB))
 		return tasks;
 
 	if (cpus_share_cache(env->dst_cpu, env->src_cpu))
@@ -10253,7 +10253,8 @@ static int detach_tasks(struct lb_env *env)
 		 * The tasks have already been sorted by order_tasks_by_llc(),
 		 * they are tasks that prefer the current LLC.
 		 */
-		if (sched_feat(SCHED_CACHE) && p->preferred_llc != -1 &&
+		if (sched_feat(SCHED_CACHE) && sched_feat(SCHED_CACHE_LB) &&
+		    p->preferred_llc != -1 &&
 		    llc_id(env->src_cpu) == p->preferred_llc)
 			break;
 #endif
@@ -10910,7 +10911,7 @@ static inline bool llc_balance(struct lb_env *env, struct sg_lb_stats *sgs,
 	struct sched_domain *child = env->sd->child;
 	int llc;
 
-	if (!sched_feat(SCHED_CACHE))
+	if (!sched_feat(SCHED_CACHE) || !sched_feat(SCHED_CACHE_LB))
 		return false;
 
 	if (env->sd->flags & SD_SHARE_LLC)
@@ -11021,7 +11022,8 @@ static void update_sg_if_llc(struct lb_env *env, struct sg_lb_stats *sgs,
 	struct sched_domain *sd = env->sd->child;
 	struct sched_domain_shared *sd_share;
 
-	if (!sched_feat(SCHED_CACHE) || env->idle == CPU_NEWLY_IDLE)
+	if (!sched_feat(SCHED_CACHE) || env->idle == CPU_NEWLY_IDLE ||
+	    !sched_feat(SCHED_CACHE_LB))
 		return;
 
 	/* only care the sched domain that spans 1 LLC */
@@ -11083,7 +11085,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			*sg_overutilized = 1;
 
 #ifdef CONFIG_SCHED_CACHE
-		if (sched_feat(SCHED_CACHE)) {
+		if (sched_feat(SCHED_CACHE) && sched_feat(SCHED_CACHE_LB)) {
 			int j;
 
 			for (j = 0; j < max_llcs; ++j)
@@ -12368,7 +12370,7 @@ imbalanced_active_balance(struct lb_env *env)
 static inline bool
 break_llc_locality(struct lb_env *env)
 {
-	if (!sched_feat(SCHED_CACHE))
+	if (!sched_feat(SCHED_CACHE) || !sched_feat(SCHED_CACHE_LB))
 		return 0;
 
 	if (cpus_share_cache(env->src_cpu, env->dst_cpu))
@@ -12870,7 +12872,7 @@ static int active_load_balance_cpu_stop(void *data)
 #ifdef CONFIG_SCHED_CACHE
 		int llc = llc_idx(target_cpu);
 
-		if (!sched_feat(SCHED_CACHE))
+		if (!sched_feat(SCHED_CACHE) || !sched_feat(SCHED_CACHE_LB))
 			goto out_unlock;
 
 		if (llc < 0)
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index d2af7bfd36bf..11dbd74cd365 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -88,6 +88,7 @@ SCHED_FEAT(TTWU_QUEUE, true)
 SCHED_FEAT(SIS_UTIL, true)
 
 SCHED_FEAT(SCHED_CACHE, true)
+SCHED_FEAT(SCHED_CACHE_LB, true)
 /*
  * Issue a WARN when we do multiple update_rq_clock() calls
  * in a single rq->lock section. Default disabled because the
-- 
2.32.0