sched: Add cluster scheduler level for x86

There are x86 CPU architectures (e.g. Jacobsville) where L2 cahce is
shared among a cluster of cores instead of being exclusive to one
single core.

To prevent oversubscription of L2 cache, load should be balanced
between such L2 clusters, especially for tasks with no shared data.
On benchmark such as SPECrate mcf test, this change provides a boost
to performance especially on medium load system on Jacobsville.  on a
Jacobsville that has 24 Atom cores, arranged into 6 clusters of 4
cores each, the benchmark number is as follow:

 Improvement over baseline kernel for mcf_r
 copies		run time	base rate
 1		-0.1%		-0.2%
 6		25.1%		25.1%
 12		18.8%		19.0%
 24		0.3%		0.3%

So this looks pretty good. In terms of the system's task distribution,
some pretty bad clumping can be seen for the vanilla kernel without
the L2 cluster domain for the 6 and 12 copies case. With the extra
domain for cluster, the load does get evened out between the clusters.

Note this patch isn't an universal win as spreading isn't necessarily
a win, particually for those workload who can benefit from packing.

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210924085104.44806-4-21cnbao@gmail.com

1 files changed, 43 insertions, 1 deletions

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 85f6e242b6b4..5094ab0bae58 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -101,6 +101,8 @@ EXPORT_PER_CPU_SYMBOL(cpu_die_map);
 
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 
+DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map);
+
 /* Per CPU bogomips and other parameters */
 DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
 EXPORT_PER_CPU_SYMBOL(cpu_info);
@@ -464,6 +466,21 @@ static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 	return false;
 }
 
+static bool match_l2c(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+{
+	int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
+
+	/* Do not match if we do not have a valid APICID for cpu: */
+	if (per_cpu(cpu_l2c_id, cpu1) == BAD_APICID)
+		return false;
+
+	/* Do not match if L2 cache id does not match: */
+	if (per_cpu(cpu_l2c_id, cpu1) != per_cpu(cpu_l2c_id, cpu2))
+		return false;
+
+	return topology_sane(c, o, "l2c");
+}
+
 /*
  * Unlike the other levels, we do not enforce keeping a
  * multicore group inside a NUMA node.  If this happens, we will
@@ -523,7 +540,7 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 }
 
 
-#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC)
+#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_CLUSTER) || defined(CONFIG_SCHED_MC)
 static inline int x86_sched_itmt_flags(void)
 {
 	return sysctl_sched_itmt_enabled ? SD_ASYM_PACKING : 0;
@@ -541,12 +558,21 @@ static int x86_smt_flags(void)
 	return cpu_smt_flags() | x86_sched_itmt_flags();
 }
 #endif
+#ifdef CONFIG_SCHED_CLUSTER
+static int x86_cluster_flags(void)
+{
+	return cpu_cluster_flags() | x86_sched_itmt_flags();
+}
+#endif
 #endif
 
 static struct sched_domain_topology_level x86_numa_in_package_topology[] = {
 #ifdef CONFIG_SCHED_SMT
 	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
 #endif
+#ifdef CONFIG_SCHED_CLUSTER
+	{ cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS) },
+#endif
 #ifdef CONFIG_SCHED_MC
 	{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
 #endif
@@ -557,6 +583,9 @@ static struct sched_domain_topology_level x86_topology[] = {
 #ifdef CONFIG_SCHED_SMT
 	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
 #endif
+#ifdef CONFIG_SCHED_CLUSTER
+	{ cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS) },
+#endif
 #ifdef CONFIG_SCHED_MC
 	{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
 #endif
@@ -584,6 +613,7 @@ void set_cpu_sibling_map(int cpu)
 	if (!has_mp) {
 		cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
 		cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
+		cpumask_set_cpu(cpu, cpu_l2c_shared_mask(cpu));
 		cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
 		cpumask_set_cpu(cpu, topology_die_cpumask(cpu));
 		c->booted_cores = 1;
@@ -602,6 +632,9 @@ void set_cpu_sibling_map(int cpu)
 		if ((i == cpu) || (has_mp && match_llc(c, o)))
 			link_mask(cpu_llc_shared_mask, cpu, i);
 
+		if ((i == cpu) || (has_mp && match_l2c(c, o)))
+			link_mask(cpu_l2c_shared_mask, cpu, i);
+
 		if ((i == cpu) || (has_mp && match_die(c, o)))
 			link_mask(topology_die_cpumask, cpu, i);
 	}
@@ -652,6 +685,11 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 	return cpu_llc_shared_mask(cpu);
 }
 
+const struct cpumask *cpu_clustergroup_mask(int cpu)
+{
+	return cpu_l2c_shared_mask(cpu);
+}
+
 static void impress_friends(void)
 {
 	int cpu;
@@ -1335,6 +1373,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
 		zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
 		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_l2c_shared_map, i), GFP_KERNEL);
 	}
 
 	/*
@@ -1564,7 +1603,10 @@ static void remove_siblinginfo(int cpu)
 
 	for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
 		cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
+	for_each_cpu(sibling, cpu_l2c_shared_mask(cpu))
+		cpumask_clear_cpu(cpu, cpu_l2c_shared_mask(sibling));
 	cpumask_clear(cpu_llc_shared_mask(cpu));
+	cpumask_clear(cpu_l2c_shared_mask(cpu));
 	cpumask_clear(topology_sibling_cpumask(cpu));
 	cpumask_clear(topology_core_cpumask(cpu));
 	cpumask_clear(topology_die_cpumask(cpu));