[RFC][PATCH 2/5] sched/fair: Make select_idle_cpu() proportional to cores

[Peter Zijlstra]

Instead of calculating how many (logical) CPUs to scan, compute how
many cores to scan.

This changes behaviour for anything !SMT2.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 kernel/sched/core.c |   19 ++++++++++++++-----
 kernel/sched/fair.c |   12 ++++++++++--
 2 files changed, 24 insertions(+), 7 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7454,11 +7454,20 @@ int sched_cpu_activate(unsigned int cpu)
 	balance_push_set(cpu, false);
 
 #ifdef CONFIG_SCHED_SMT
-	/*
-	 * When going up, increment the number of cores with SMT present.
-	 */
-	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
-		static_branch_inc_cpuslocked(&sched_smt_present);
+	do {
+		int weight = cpumask_weight(cpu_smt_mask(cpu));
+		extern int sched_smt_weight;
+
+		if (weight > sched_smt_weight)
+			sched_smt_weight = weight;
+
+		/*
+		 * When going up, increment the number of cores with SMT present.
+		 */
+		if (weight == 2)
+			static_branch_inc_cpuslocked(&sched_smt_present);
+
+	} while (0);
 #endif
 	set_cpu_active(cpu, true);
 
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6010,6 +6010,8 @@ static inline int find_idlest_cpu(struct
 DEFINE_STATIC_KEY_FALSE(sched_smt_present);
 EXPORT_SYMBOL_GPL(sched_smt_present);
 
+int sched_smt_weight = 1;
+
 static inline void set_idle_cores(int cpu, int val)
 {
 	struct sched_domain_shared *sds;
@@ -6124,6 +6126,8 @@ static int select_idle_smt(struct task_s
 
 #else /* CONFIG_SCHED_SMT */
 
+#define sched_smt_weight	1
+
 static inline int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	return -1;
@@ -6136,6 +6140,8 @@ static inline int select_idle_smt(struct
 
 #endif /* CONFIG_SCHED_SMT */
 
+#define sis_min_cores		2
+
 /*
  * Scan the LLC domain for idle CPUs; this is dynamically regulated by
  * comparing the average scan cost (tracked in sd->avg_scan_cost) against the
@@ -6166,10 +6172,12 @@ static int select_idle_cpu(struct task_s
 		avg_cost = this_sd->avg_scan_cost + 1;
 
 		span_avg = sd->span_weight * avg_idle;
-		if (span_avg > 4*avg_cost)
+		if (span_avg > sis_min_cores * avg_cost)
 			nr = div_u64(span_avg, avg_cost);
 		else
-			nr = 4;
+			nr = sis_min_cores;
+
+		nr *= sched_smt_weight;
 
 		time = cpu_clock(this);
 	}