From nobody Tue Dec 16 13:53:30 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id A0A48CDB47E for ; Thu, 12 Oct 2023 12:20:07 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1378533AbjJLMUH (ORCPT ); Thu, 12 Oct 2023 08:20:07 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:44530 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233709AbjJLMUC (ORCPT ); Thu, 12 Oct 2023 08:20:02 -0400 Received: from szxga01-in.huawei.com (szxga01-in.huawei.com [45.249.212.187]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 15BC0BA for ; Thu, 12 Oct 2023 05:20:00 -0700 (PDT) Received: from canpemm500009.china.huawei.com (unknown [172.30.72.57]) by szxga01-in.huawei.com (SkyGuard) with ESMTP id 4S5pYG1p0rzrTN6; Thu, 12 Oct 2023 20:17:22 +0800 (CST) Received: from localhost.localdomain (10.50.163.32) by canpemm500009.china.huawei.com (7.192.105.203) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.31; Thu, 12 Oct 2023 20:19:57 +0800 From: Yicong Yang To: , , , , , , , , , , , CC: , , , , , , , , , <21cnbao@gmail.com>, , Subject: [PATCH v10 1/3] sched: Add cpus_share_resources API Date: Thu, 12 Oct 2023 20:17:05 +0800 Message-ID: <20231012121707.51368-2-yangyicong@huawei.com> X-Mailer: git-send-email 2.31.0 In-Reply-To: <20231012121707.51368-1-yangyicong@huawei.com> References: <20231012121707.51368-1-yangyicong@huawei.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Originating-IP: [10.50.163.32] X-ClientProxiedBy: dggems704-chm.china.huawei.com (10.3.19.181) To canpemm500009.china.huawei.com (7.192.105.203) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" From: Barry Song Add cpus_share_resources() API. This is the preparation for the optimization of select_idle_cpu() on platforms with cluster scheduler level. On a machine with clusters cpus_share_resources() will test whether two cpus are within the same cluster. On a non-cluster machine it will behaves the same as cpus_share_cache(). So we use "resources" here for cache resources. Tested-by: K Prateek Nayak Signed-off-by: Barry Song Signed-off-by: Yicong Yang Reviewed-by: Gautham R. Shenoy Reviewed-by: Tim Chen Reviewed-by: Vincent Guittot --- include/linux/sched/sd_flags.h | 7 +++++++ include/linux/sched/topology.h | 8 +++++++- kernel/sched/core.c | 12 ++++++++++++ kernel/sched/sched.h | 1 + kernel/sched/topology.c | 13 +++++++++++++ 5 files changed, 40 insertions(+), 1 deletion(-) diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index fad77b5172e2..a8b28647aafc 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -109,6 +109,13 @@ SD_FLAG(SD_ASYM_CPUCAPACITY_FULL, SDF_SHARED_PARENT | = SDF_NEEDS_GROUPS) */ SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) =20 +/* + * Domain members share CPU cluster (LLC tags or L2 cache) + * + * NEEDS_GROUPS: Clusters are shared between groups. + */ +SD_FLAG(SD_CLUSTER, SDF_NEEDS_GROUPS) + /* * Domain members share CPU package resources (i.e. caches) * diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 67b573d5bf28..4c14fe127223 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -45,7 +45,7 @@ static inline int cpu_smt_flags(void) #ifdef CONFIG_SCHED_CLUSTER static inline int cpu_cluster_flags(void) { - return SD_SHARE_PKG_RESOURCES; + return SD_CLUSTER | SD_SHARE_PKG_RESOURCES; } #endif =20 @@ -179,6 +179,7 @@ cpumask_var_t *alloc_sched_domains(unsigned int ndoms); void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); =20 bool cpus_share_cache(int this_cpu, int that_cpu); +bool cpus_share_resources(int this_cpu, int that_cpu); =20 typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); typedef int (*sched_domain_flags_f)(void); @@ -232,6 +233,11 @@ static inline bool cpus_share_cache(int this_cpu, int = that_cpu) return true; } =20 +static inline bool cpus_share_resources(int this_cpu, int that_cpu) +{ + return true; +} + #endif /* !CONFIG_SMP */ =20 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a3f9cd52eec5..e1b5b87dd48a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3935,6 +3935,18 @@ bool cpus_share_cache(int this_cpu, int that_cpu) return per_cpu(sd_llc_id, this_cpu) =3D=3D per_cpu(sd_llc_id, that_cpu); } =20 +/* + * Whether CPUs are share cache resources, which means LLC on non-cluster + * machines and LLC tag or L2 on machines with clusters. + */ +bool cpus_share_resources(int this_cpu, int that_cpu) +{ + if (this_cpu =3D=3D that_cpu) + return true; + + return per_cpu(sd_share_id, this_cpu) =3D=3D per_cpu(sd_share_id, that_cp= u); +} + static inline bool ttwu_queue_cond(struct task_struct *p, int cpu) { /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 65cad0e5729e..998f03d02de0 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1853,6 +1853,7 @@ static inline struct sched_domain *lowest_flag_domain= (int cpu, int flag) DECLARE_PER_CPU(struct sched_domain __rcu *, sd_llc); DECLARE_PER_CPU(int, sd_llc_size); DECLARE_PER_CPU(int, sd_llc_id); +DECLARE_PER_CPU(int, sd_share_id); DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared); DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa); DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing); diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index d9508617f7f8..48cd88350d18 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -668,6 +668,7 @@ static void destroy_sched_domains(struct sched_domain *= sd) DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc); DEFINE_PER_CPU(int, sd_llc_size); DEFINE_PER_CPU(int, sd_llc_id); +DEFINE_PER_CPU(int, sd_share_id); DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared); DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa); DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing); @@ -693,6 +694,17 @@ static void update_top_cache_domain(int cpu) per_cpu(sd_llc_id, cpu) =3D id; rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds); =20 + sd =3D lowest_flag_domain(cpu, SD_CLUSTER); + if (sd) + id =3D cpumask_first(sched_domain_span(sd)); + + /* + * This assignment should be placed after the sd_llc_id as + * we want this id equals to cluster id on cluster machines + * but equals to LLC id on non-Cluster machines. + */ + per_cpu(sd_share_id, cpu) =3D id; + sd =3D lowest_flag_domain(cpu, SD_NUMA); rcu_assign_pointer(per_cpu(sd_numa, cpu), sd); =20 @@ -1550,6 +1562,7 @@ static struct cpumask ***sched_domains_numa_masks; */ #define TOPOLOGY_SD_FLAGS \ (SD_SHARE_CPUCAPACITY | \ + SD_CLUSTER | \ SD_SHARE_PKG_RESOURCES | \ SD_NUMA | \ SD_ASYM_PACKING) --=20 2.24.0