[RFC][PATCH 7/7] sched: debug muck -- not for merging

[Peter Zijlstra]

Add a few knobs to poke while playing with the new code.

Not-Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 include/linux/sched/sysctl.h |    1 
 kernel/sched/fair.c          |   86 ++++++++++++++++++++++++++++++++++---------
 kernel/sched/features.h      |   10 +++++
 kernel/sysctl.c              |    7 +++
 4 files changed, 86 insertions(+), 18 deletions(-)

--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -37,6 +37,7 @@ extern unsigned int sysctl_sched_migrati
 extern unsigned int sysctl_sched_nr_migrate;
 extern unsigned int sysctl_sched_time_avg;
 extern unsigned int sysctl_sched_shares_window;
+extern unsigned int sysctl_sched_shift;
 
 int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *length,
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -114,6 +114,8 @@ unsigned int __read_mostly sysctl_sched_
 unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
 #endif
 
+const_debug unsigned int sysctl_sched_shift = 9;
+
 static inline void update_load_add(struct load_weight *lw, unsigned long inc)
 {
 	lw->weight += inc;
@@ -5354,18 +5356,24 @@ static inline int select_idle_smt(struct
 static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	struct sched_domain *this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
-	u64 avg_idle = this_rq()->avg_idle;
-	u64 avg_cost = this_sd->avg_scan_cost;
 	u64 time, cost;
 	s64 delta;
 	int cpu, wrap;
 
-	/*
-	 * Due to large variance we need a large fuzz factor; hackbench in
-	 * particularly is sensitive here.
-	 */
-	if ((avg_idle / 512) < avg_cost)
-		return -1;
+	if (sched_feat(AVG_CPU)) {
+		u64 avg_idle = this_rq()->avg_idle;
+		u64 avg_cost = this_sd->avg_scan_cost;
+
+		if (sched_feat(PRINT_AVG))
+			trace_printk("idle: %Ld cost: %Ld\n", avg_idle, avg_cost);
+
+		/*
+		 * Due to large variance we need a large fuzz factor; hackbench in
+		 * particularly is sensitive here.
+		 */
+		if ((avg_idle >> sysctl_sched_shift) < avg_cost)
+			return -1;
+	}
 
 	time = local_clock();
 
@@ -5379,6 +5387,7 @@ static int select_idle_cpu(struct task_s
 	time = local_clock() - time;
 	cost = this_sd->avg_scan_cost;
 	delta = (s64)(time - cost) / 8;
+	/* trace_printk("time: %Ld cost: %Ld delta: %Ld\n", time, cost, delta); */
 	this_sd->avg_scan_cost += delta;
 
 	return cpu;
@@ -5390,7 +5399,7 @@ static int select_idle_cpu(struct task_s
 static int select_idle_sibling(struct task_struct *p, int target)
 {
 	struct sched_domain *sd;
-	int i = task_cpu(p);
+	int start, i = task_cpu(p);
 
 	if (idle_cpu(target))
 		return target;
@@ -5401,21 +5410,62 @@ static int select_idle_sibling(struct ta
 	if (i != target && cpus_share_cache(i, target) && idle_cpu(i))
 		return i;
 
+	start = target;
+	if (sched_feat(ORDER_IDLE))
+		start = per_cpu(sd_llc_id, target); /* first cpu in llc domain */
+
 	sd = rcu_dereference(per_cpu(sd_llc, target));
 	if (!sd)
 		return target;
 
-	i = select_idle_core(p, sd, target);
-	if ((unsigned)i < nr_cpumask_bits)
-		return i;
+	if (sched_feat(OLD_IDLE)) {
+		struct sched_group *sg;
 
-	i = select_idle_cpu(p, sd, target);
-	if ((unsigned)i < nr_cpumask_bits)
-		return i;
+		for_each_lower_domain(sd) {
+			sg = sd->groups;
+			do {
+				if (!cpumask_intersects(sched_group_cpus(sg),
+							tsk_cpus_allowed(p)))
+					goto next;
+
+				/* Ensure the entire group is idle */
+				for_each_cpu(i, sched_group_cpus(sg)) {
+					if (i == target || !idle_cpu(i))
+						goto next;
+				}
 
-	i = select_idle_smt(p, sd, target);
-	if ((unsigned)i < nr_cpumask_bits)
-		return i;
+				/*
+				 * It doesn't matter which cpu we pick, the
+				 * whole group is idle.
+				 */
+				target = cpumask_first_and(sched_group_cpus(sg),
+						tsk_cpus_allowed(p));
+				goto done;
+next:
+				sg = sg->next;
+			} while (sg != sd->groups);
+		}
+done:
+		return target;
+	}
+
+	if (sched_feat(IDLE_CORE)) {
+		i = select_idle_core(p, sd, start);
+		if ((unsigned)i < nr_cpumask_bits)
+			return i;
+	}
+
+	if (sched_feat(IDLE_CPU)) {
+		i = select_idle_cpu(p, sd, start);
+		if ((unsigned)i < nr_cpumask_bits)
+			return i;
+	}
+
+	if (sched_feat(IDLE_SMT)) {
+		i = select_idle_smt(p, sd, start);
+		if ((unsigned)i < nr_cpumask_bits)
+			return i;
+	}
 
 	return target;
 }
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -69,3 +69,13 @@ SCHED_FEAT(RT_RUNTIME_SHARE, true)
 SCHED_FEAT(LB_MIN, false)
 SCHED_FEAT(ATTACH_AGE_LOAD, true)
 
+SCHED_FEAT(OLD_IDLE, false)
+SCHED_FEAT(ORDER_IDLE, false)
+
+SCHED_FEAT(IDLE_CORE, true)
+SCHED_FEAT(IDLE_CPU, true)
+SCHED_FEAT(AVG_CPU, true)
+SCHED_FEAT(PRINT_AVG, false)
+
+SCHED_FEAT(IDLE_SMT, true)
+
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -334,6 +334,13 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
+		.procname	= "sched_shift",
+		.data		= &sysctl_sched_shift,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
 		.procname	= "sched_nr_migrate",
 		.data		= &sysctl_sched_nr_migrate,
 		.maxlen		= sizeof(unsigned int),