The following commit has been merged into the sched/core branch of tip:
Commit-ID: b95303e0aeaf446b65169dd4142cacdaeb7d4c8b
Gitweb: https://git.kernel.org/tip/b95303e0aeaf446b65169dd4142cacdaeb7d4c8b
Author: Barry Song <song.bao.hua@hisilicon.com>
AuthorDate: Thu, 19 Oct 2023 11:33:21 +08:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Tue, 24 Oct 2023 10:38:42 +02:00
sched: Add cpus_share_resources API
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.
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
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>
Tested-and-reviewed-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lkml.kernel.org/r/20231019033323.54147-2-yangyicong@huawei.com
---
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(-)
@@ -110,6 +110,13 @@ 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)
*
* SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
@@ -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)
@@ -3939,6 +3939,18 @@ 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)
{
/*
@@ -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);
@@ -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) = 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);
@@ -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)