From: Yicong Yang <yangyicong@huawei.com>
To: <peterz@infradead.org>, <mingo@redhat.com>,
<juri.lelli@redhat.com>, <vincent.guittot@linaro.org>,
<dietmar.eggemann@arm.com>, <tim.c.chen@linux.intel.com>,
<yu.c.chen@intel.com>, <gautham.shenoy@amd.com>,
<mgorman@suse.de>, <vschneid@redhat.com>,
<linux-kernel@vger.kernel.org>,
<linux-arm-kernel@lists.infradead.org>
Cc: <rostedt@goodmis.org>, <bsegall@google.com>, <bristot@redhat.com>,
<prime.zeng@huawei.com>, <yangyicong@hisilicon.com>,
<jonathan.cameron@huawei.com>, <ego@linux.vnet.ibm.com>,
<srikar@linux.vnet.ibm.com>, <linuxarm@huawei.com>,
<21cnbao@gmail.com>, <kprateek.nayak@amd.com>,
<wuyun.abel@bytedance.com>,
Barry Song <song.bao.hua@hisilicon.com>
Subject: [PATCH v9 1/2] sched: Add cpus_share_resources API
Date: Wed, 19 Jul 2023 17:28:37 +0800 [thread overview]
Message-ID: <20230719092838.2302-2-yangyicong@huawei.com> (raw)
In-Reply-To: <20230719092838.2302-1-yangyicong@huawei.com>
From: Barry Song <song.bao.hua@hisilicon.com>
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 <kprateek.nayak@amd.com>
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
---
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)
+/*
+ * 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
@@ -179,6 +179,7 @@ cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
bool cpus_share_cache(int this_cpu, int that_cpu);
+bool cpus_share_resources(int this_cpu, int that_cpu);
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;
}
+static inline bool cpus_share_resources(int this_cpu, int that_cpu)
+{
+ return true;
+}
+
#endif /* !CONFIG_SMP */
#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c52c2eba7c73..4e88643dc48c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3953,6 +3953,18 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
}
+/*
+ * 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 == that_cpu)
+ return true;
+
+ return per_cpu(sd_share_id, this_cpu) == per_cpu(sd_share_id, that_cpu);
+}
+
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 e93e006a942b..4ff8cdc5a55a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1847,6 +1847,7 @@ 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 d3a3b2646ec4..ce1fd8e00346 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -666,6 +666,7 @@ 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);
@@ -691,6 +692,17 @@ static void update_top_cache_domain(int cpu)
per_cpu(sd_llc_id, cpu) = id;
rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);
+ sd = lowest_flag_domain(cpu, SD_CLUSTER);
+ if (sd)
+ id = 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) = id;
+
sd = lowest_flag_domain(cpu, SD_NUMA);
rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
@@ -1539,6 +1551,7 @@ 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)
--
2.24.0
next prev parent reply other threads:[~2023-07-19 9:31 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-19 9:28 [PATCH v9 0/2] sched/fair: Scan cluster before scanning LLC in wake-up path Yicong Yang
2023-07-19 9:28 ` Yicong Yang [this message]
2023-07-19 9:28 ` [PATCH v9 2/2] " Yicong Yang
2023-07-21 9:52 ` Chen Yu
2023-08-01 12:06 ` Yicong Yang
2023-08-04 16:29 ` Chen Yu
2023-08-07 13:15 ` Yicong Yang
2023-08-15 11:16 ` [PATCH v9 0/2] " Yicong Yang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230719092838.2302-2-yangyicong@huawei.com \
--to=yangyicong@huawei.com \
--cc=21cnbao@gmail.com \
--cc=bristot@redhat.com \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=ego@linux.vnet.ibm.com \
--cc=gautham.shenoy@amd.com \
--cc=jonathan.cameron@huawei.com \
--cc=juri.lelli@redhat.com \
--cc=kprateek.nayak@amd.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxarm@huawei.com \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=prime.zeng@huawei.com \
--cc=rostedt@goodmis.org \
--cc=song.bao.hua@hisilicon.com \
--cc=srikar@linux.vnet.ibm.com \
--cc=tim.c.chen@linux.intel.com \
--cc=vincent.guittot@linaro.org \
--cc=vschneid@redhat.com \
--cc=wuyun.abel@bytedance.com \
--cc=yangyicong@hisilicon.com \
--cc=yu.c.chen@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).