sched: Consider PF_WAKE_UP_IDLE in select_best_cpu()

sysctl_sched_prefer_idle controls selection of idle cpus for waking
tasks. In some cases, waking to idle cpus help performance while in
other cases it hurts (as tasks incur latency associated with C-state
wakeup). Its ideal if scheduler can adapt prefer_idle behavior based
on the task that is waking up, but that's hard for scheduler to
figure by itself. PF_WAKE_UP_IDLE hint can be provided by external
module/driver in such case to guide scheduler in preferring an idle
cpu for select tasks irrespective of sysctl_sched_prefer_idle flag.

This patch enhances select_best_cpu() to consider PF_WAKE_UP_IDLE
hint. Wakeup posted from any task that has PF_WAKE_UP_IDLE set is a
hint for scheduler to prefer idle cpu for waking tasks. Similarly
scheduler will attempt to place any task with PF_WAKE_UP_IDLE set on
idle cpu when they wakeup.

CRs-Fixed: 773101
Change-Id: Ia8bf334d98fd9fd2ff9eda875430497d55d64ce6
Signed-off-by: Srivatsa Vaddagiri <vatsa@codeaurora.org>

1 files changed, 22 insertions, 1 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d9d4694d58da..4260cb552d9f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3230,6 +3230,20 @@ static int select_packing_target(struct task_struct *p, int best_cpu)
 	return target;
 }
 
+/*
+ * Should task be woken to any available idle cpu?
+ *
+ * Waking tasks to idle cpu has mixed implications on both performance and
+ * power. In many cases, scheduler can't estimate correctly impact of using idle
+ * cpus on either performance or power. PF_WAKE_UP_IDLE allows external kernel
+ * module to pass a strong hint to scheduler that the task in question should be
+ * woken to idle cpu, generally to improve performance.
+ */
+static inline int wake_to_idle(struct task_struct *p)
+{
+	return (current->flags & PF_WAKE_UP_IDLE) ||
+			 (p->flags & PF_WAKE_UP_IDLE);
+}
 
 /* return cheapest cpu that can fit this task */
 static int select_best_cpu(struct task_struct *p, int target, int reason,
@@ -3245,6 +3259,13 @@ static int select_best_cpu(struct task_struct *p, int target, int reason,
 	int cstate, min_cstate = INT_MAX;
 	int prefer_idle = reason ? 1 : sysctl_sched_prefer_idle;
 	int curr_cpu = smp_processor_id();
+	int prefer_idle_override = 0;
+
+	if (wake_to_idle(p)) {
+		prefer_idle = 1;
+		prefer_idle_override = 1;
+		small_task = 0;
+	}
 
 	trace_sched_task_load(p, small_task, boost, reason, sync, prefer_idle);
 
@@ -3377,7 +3398,7 @@ done:
 			best_cpu = fallback_idle_cpu;
 	}
 
-	if (cpu_rq(best_cpu)->mostly_idle_freq)
+	if (cpu_rq(best_cpu)->mostly_idle_freq && !prefer_idle_override)
 		best_cpu = select_packing_target(p, best_cpu);
 
 	return best_cpu;