[PATCH v2 3/8] sched/fair: Update idle-core more often

[Srikar Dronamraju]

Currently when the scheduler does a load balance and pulls a task or
when a CPU picks up a task during wakeup without having to call
select_idle_cpu(), it never checks if the target CPU is part of the
idle-core. This makes idle-core less accurate.

Given that the identity of idle-core for LLC is maintained, its easy to
update the idle-core as soon as the CPU picks up a task.

This change will update the idle-core whenever a CPU from the idle-core
picks up a task. However if there are multiple idle-cores in the LLC,
and waking CPU happens to be part of the designated idle-core, idle-core
is set to -1. In cases where the scheduler is sure that there are no
more idle-cores, idle-core is set to -2.

To reduce this case, whenever a CPU updates idle-core, it will look for
other cores in the LLC for an idle-core, if the core to which it belongs
to is not idle.

Cc: LKML <linux-kernel@xxxxxxxxxxxxxxx>
Cc: Gautham R Shenoy <ego@xxxxxxxxxxxxxxxxxx>
Cc: Parth Shah <parth@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Valentin Schneider <valentin.schneider@xxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxxx>
Signed-off-by: Srikar Dronamraju <srikar@xxxxxxxxxxxxxxxxxx>
---
 kernel/sched/fair.c  | 54 +++++++++++++++++++++++++++++++++++++++++---
 kernel/sched/idle.c  |  6 +++++
 kernel/sched/sched.h |  2 ++
 3 files changed, 59 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8c9d1a210820..50da2363317d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6015,6 +6015,13 @@ static inline int __select_idle_cpu(int cpu)
 DEFINE_STATIC_KEY_FALSE(sched_smt_present);
 EXPORT_SYMBOL_GPL(sched_smt_present);
 
+/*
+ * Value of -2 indicates there are no idle-cores in LLC.
+ * Value of -1 indicates an idle-core turned to busy recently.
+ * However there could be other idle-cores in the system.
+ * Anyother value indicates core to which the CPU(value)
+ * belongs is idle.
+ */
 static inline void set_idle_core(int cpu, int val)
 {
 	struct sched_domain_shared *sds;
@@ -6037,6 +6044,40 @@ static inline int get_idle_core(int cpu, int def)
 	return def;
 }
 
+static void set_next_idle_core(struct sched_domain *sd, int target)
+{
+	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
+	int core, cpu;
+
+	cpumask_andnot(cpus, sched_domain_span(sd), cpu_smt_mask(target));
+	for_each_cpu_wrap(core, cpus, target) {
+		bool idle = true;
+
+		for_each_cpu(cpu, cpu_smt_mask(core)) {
+			if (!available_idle_cpu(cpu)) {
+				idle = false;
+				break;
+			}
+		}
+
+		if (idle) {
+			set_idle_core(core, per_cpu(smt_id, core));
+			return;
+		}
+
+		cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
+	}
+	set_idle_core(target, -2);
+}
+
+void set_core_busy(int core)
+{
+	rcu_read_lock();
+	if (get_idle_core(core, -1) == per_cpu(smt_id, core))
+		set_idle_core(core, -1);
+	rcu_read_unlock();
+}
+
 /*
  * Scans the local SMT mask to see if the entire core is idle, and records this
  * information in sd_llc_shared->idle_core.
@@ -6046,11 +6087,13 @@ static inline int get_idle_core(int cpu, int def)
  */
 void __update_idle_core(struct rq *rq)
 {
+	struct sched_domain *sd;
 	int core = cpu_of(rq);
 	int cpu;
 
 	rcu_read_lock();
-	if (get_idle_core(core, 0) >= 0)
+	sd = rcu_dereference(per_cpu(sd_llc, core));
+	if (!sd || get_idle_core(core, 0) >= 0)
 		goto unlock;
 
 	for_each_cpu(cpu, cpu_smt_mask(core)) {
@@ -6058,10 +6101,15 @@ void __update_idle_core(struct rq *rq)
 			continue;
 
 		if (!available_idle_cpu(cpu))
-			goto unlock;
+			goto try_next;
 	}
 
 	set_idle_core(core, per_cpu(smt_id, core));
+	goto unlock;
+
+try_next:
+	set_next_idle_core(sd, core);
+
 unlock:
 	rcu_read_unlock();
 }
@@ -6130,7 +6178,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
 	int i, cpu, idle_cpu = -1, nr = INT_MAX;
 	int idle_core = get_idle_core(target, -1);
-	bool smt = (idle_core != -1);
+	bool smt = (idle_core != -2);
 	int this = smp_processor_id();
 	struct sched_domain *this_sd;
 	u64 time;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 7199e6f23789..cc828f3efe71 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -425,6 +425,12 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
+#ifdef CONFIG_SCHED_SMT
+	int cpu = rq->cpu;
+
+	if (static_branch_likely(&sched_smt_present))
+		set_core_busy(cpu);
+#endif
 }
 
 static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 46d40a281724..5c0bd4b0e73a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1102,6 +1102,7 @@ static inline bool is_migration_disabled(struct task_struct *p)
 
 #ifdef CONFIG_SCHED_SMT
 extern void __update_idle_core(struct rq *rq);
+extern void set_core_busy(int cpu);
 
 static inline void update_idle_core(struct rq *rq)
 {
@@ -1111,6 +1112,7 @@ static inline void update_idle_core(struct rq *rq)
 
 #else
 static inline void update_idle_core(struct rq *rq) { }
+static inline void set_core_busy(int cpu) { }
 #endif
 
 DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-- 
2.18.2