linux-kernel - [PATCH 01/17] sched/fair: Enable group_asym_packing in find_idlest

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: <20251204175405.1511340-2-srikar@linux.ibm.com>
Date: Thu,  4 Dec 2025 23:23:49 +0530
From: Srikar Dronamraju <srikar@...ux.ibm.com>
To: linux-kernel@...r.kernel.org, linuxppc-dev@...ts.ozlabs.org,
        Peter Zijlstra <peterz@...radead.org>
Cc: Ben Segall <bsegall@...gle.com>,
        Christophe Leroy <christophe.leroy@...roup.eu>,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Ingo Molnar <mingo@...nel.org>, Juri Lelli <juri.lelli@...hat.com>,
        K Prateek Nayak <kprateek.nayak@....com>,
        Madhavan Srinivasan <maddy@...ux.ibm.com>,
        Mel Gorman <mgorman@...e.de>, Michael Ellerman <mpe@...erman.id.au>,
        Nicholas Piggin <npiggin@...il.com>,
        Shrikanth Hegde <sshegde@...ux.ibm.com>,
        Srikar Dronamraju <srikar@...ux.ibm.com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Swapnil Sapkal <swapnil.sapkal@....com>,
        Thomas Huth <thuth@...hat.com>,
        Valentin Schneider <vschneid@...hat.com>,
        Vincent Guittot <vincent.guittot@...aro.org>,
        virtualization@...ts.linux.dev, Yicong Yang <yangyicong@...ilicon.com>,
        Ilya Leoshkevich <iii@...ux.ibm.com>
Subject: [PATCH 01/17] sched/fair: Enable group_asym_packing in find_idlest_group

Current scheduler code doesn't handle SD_ASYM_PACKING in the
find_idlest_cpu path. On few architectures, like Powerpc, cache is at a
core. Moving threads across cores may end up in cache misses.

While asym_packing can be enabled above SMT level, enabling Asym packing
across cores could result in poorer performance due to cache misses.
However if the initial task placement via find_idlest_cpu does take
asym_packing into consideration, then scheduler can avoid asym_packing
migrations. This will result in lesser migrations and better packing and
better overall performance.

Previous version was posted at
https://lore.kernel.org/all/20231018155036.2314342-1-srikar@linux.vnet.ibm.com/t

Signed-off-by: Srikar Dronamraju <srikar@...ux.ibm.com>
---
 kernel/sched/fair.c | 33 ++++++++++++++++++++++++++++-----
 1 file changed, 28 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5b752324270b..979c3e333fba 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10664,11 +10664,13 @@ static int idle_cpu_without(int cpu, struct task_struct *p)
  * @group: sched_group whose statistics are to be updated.
  * @sgs: variable to hold the statistics for this group.
  * @p: The task for which we look for the idlest group/CPU.
+ * @this_cpu: current cpu
  */
 static inline void update_sg_wakeup_stats(struct sched_domain *sd,
 					  struct sched_group *group,
 					  struct sg_lb_stats *sgs,
-					  struct task_struct *p)
+					  struct task_struct *p,
+					  int asym_prefer_cpu)
 {
 	int i, nr_running;
 
@@ -10705,6 +10707,12 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
 
 	}
 
+	if (asym_prefer_cpu != READ_ONCE(group->asym_prefer_cpu) &&
+			sched_asym(sd, READ_ONCE(group->asym_prefer_cpu),
+			READ_ONCE(asym_prefer_cpu))) {
+		sgs->group_asym_packing = 1;
+	}
+
 	sgs->group_capacity = group->sgc->capacity;
 
 	sgs->group_weight = group->group_weight;
@@ -10721,7 +10729,8 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
 				sgs->group_capacity;
 }
 
-static bool update_pick_idlest(struct sched_group *idlest,
+static bool update_pick_idlest(struct sched_domain *sd,
+			       struct sched_group *idlest,
 			       struct sg_lb_stats *idlest_sgs,
 			       struct sched_group *group,
 			       struct sg_lb_stats *sgs)
@@ -10745,8 +10754,11 @@ static bool update_pick_idlest(struct sched_group *idlest,
 			return false;
 		break;
 
-	case group_imbalanced:
 	case group_asym_packing:
+		return sched_asym(sd, READ_ONCE(group->asym_prefer_cpu),
+				READ_ONCE(idlest->asym_prefer_cpu));
+
+	case group_imbalanced:
 	case group_smt_balance:
 		/* Those types are not used in the slow wakeup path */
 		return false;
@@ -10790,6 +10802,7 @@ sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int
 			.avg_load = UINT_MAX,
 			.group_type = group_overloaded,
 	};
+	int asym_prefer_cpu;
 
 	do {
 		int local_group;
@@ -10812,10 +10825,12 @@ sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int
 		} else {
 			sgs = &tmp_sgs;
 		}
+		if (!local || local_group)
+			asym_prefer_cpu = READ_ONCE(group->asym_prefer_cpu);
 
-		update_sg_wakeup_stats(sd, group, sgs, p);
+		update_sg_wakeup_stats(sd, group, sgs, p, asym_prefer_cpu);
 
-		if (!local_group && update_pick_idlest(idlest, &idlest_sgs, group, sgs)) {
+		if (!local_group && update_pick_idlest(sd, idlest, &idlest_sgs, group, sgs)) {
 			idlest = group;
 			idlest_sgs = *sgs;
 		}
@@ -10845,6 +10860,14 @@ sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int
 	if (local_sgs.group_type > idlest_sgs.group_type)
 		return idlest;
 
+	if (idlest_sgs.group_type == group_asym_packing) {
+		if (sched_asym(sd, READ_ONCE(idlest->asym_prefer_cpu),
+				READ_ONCE(local->asym_prefer_cpu))) {
+			return idlest;
+		}
+		return NULL;
+	}
+
 	switch (local_sgs.group_type) {
 	case group_overloaded:
 	case group_fully_busy:
-- 
2.43.7