[PATCH 15/17] [RFC] sched/eevdf: Sleeper bonus

[Peter Zijlstra]

Add a sleeper bonus hack, but keep it default disabled. This should
allow easy testing if regressions are due to this.

Specifically; this 'restores' performance for things like starve and
stress-futex, stress-nanosleep that rely on sleeper bonus to compete
against an always running parent (the fair 67%/33% split vs the
50%/50% bonus thing).

OTOH this completely destroys latency and hackbench (as in 5x worse).

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 kernel/sched/fair.c     |   47 ++++++++++++++++++++++++++++++++++++++++-------
 kernel/sched/features.h |    1 +
 kernel/sched/sched.h    |    3 ++-
 3 files changed, 43 insertions(+), 8 deletions(-)

--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4819,7 +4819,7 @@ static inline void update_misfit_status(
 #endif /* CONFIG_SMP */
 
 static void
-place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
+place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	u64 vslice = calc_delta_fair(se->slice, se);
 	u64 vruntime = avg_vruntime(cfs_rq);
@@ -4878,22 +4878,55 @@ place_entity(struct cfs_rq *cfs_rq, stru
 		if (WARN_ON_ONCE(!load))
 			load = 1;
 		lag = div_s64(lag, load);
+
+		vruntime -= lag;
+	}
+
+	/*
+	 * Base the deadline on the 'normal' EEVDF placement policy in an
+	 * attempt to not let the bonus crud below wreck things completely.
+	 */
+	se->deadline = vruntime;
+
+	/*
+	 * The whole 'sleeper' bonus hack... :-/ This is strictly unfair.
+	 *
+	 * By giving a sleeping task a little boost, it becomes possible for a
+	 * 50% task to compete equally with a 100% task. That is, strictly fair
+	 * that setup would result in a 67% / 33% split. Sleeper bonus will
+	 * change that to 50% / 50%.
+	 *
+	 * This thing hurts my brain, because tasks leaving with negative lag
+	 * will move 'time' backward, so comparing against a historical
+	 * se->vruntime is dodgy as heck.
+	 */
+	if (sched_feat(PLACE_BONUS) &&
+	    (flags & ENQUEUE_WAKEUP) && !(flags & ENQUEUE_MIGRATED)) {
+		/*
+		 * If se->vruntime is ahead of vruntime, something dodgy
+		 * happened and we cannot give bonus due to not having valid
+		 * history.
+		 */
+		if ((s64)(se->vruntime - vruntime) < 0) {
+			vruntime -= se->slice/2;
+			vruntime = max_vruntime(se->vruntime, vruntime);
+		}
 	}
 
-	se->vruntime = vruntime - lag;
+	se->vruntime = vruntime;
 
 	/*
 	 * When joining the competition; the exisiting tasks will be,
 	 * on average, halfway through their slice, as such start tasks
 	 * off with half a slice to ease into the competition.
 	 */
-	if (sched_feat(PLACE_DEADLINE_INITIAL) && initial)
+	if (sched_feat(PLACE_DEADLINE_INITIAL) && (flags & ENQUEUE_INITIAL))
 		vslice /= 2;
 
 	/*
 	 * EEVDF: vd_i = ve_i + r_i/w_i
 	 */
-	se->deadline = se->vruntime + vslice;
+	se->deadline += vslice;
 }
 
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
@@ -4910,7 +4943,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, st
 	 * update_curr().
 	 */
 	if (curr)
-		place_entity(cfs_rq, se, 0);
+		place_entity(cfs_rq, se, flags);
 
 	update_curr(cfs_rq);
 
@@ -4937,7 +4970,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, st
 	 * we can place the entity.
 	 */
 	if (!curr)
-		place_entity(cfs_rq, se, 0);
+		place_entity(cfs_rq, se, flags);
 
 	account_entity_enqueue(cfs_rq, se);
 
@@ -11933,7 +11966,7 @@ static void task_fork_fair(struct task_s
 	curr = cfs_rq->curr;
 	if (curr)
 		update_curr(cfs_rq);
-	place_entity(cfs_rq, se, 1);
+	place_entity(cfs_rq, se, ENQUEUE_INITIAL);
 	rq_unlock(rq, &rf);
 }
 
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -7,6 +7,7 @@
 SCHED_FEAT(PLACE_LAG, true)
 SCHED_FEAT(PLACE_FUDGE, true)
 SCHED_FEAT(PLACE_DEADLINE_INITIAL, true)
+SCHED_FEAT(PLACE_BONUS, false)
 
 /*
  * Prefer to schedule the task we woke last (assuming it failed
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2143,7 +2143,7 @@ extern const u32		sched_prio_to_wmult[40
  * ENQUEUE_HEAD      - place at front of runqueue (tail if not specified)
  * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline)
  * ENQUEUE_MIGRATED  - the task was migrated during wakeup
- *
+ * ENQUEUE_INITIAL   - place a new task (fork/clone)
  */
 
 #define DEQUEUE_SLEEP		0x01
@@ -2163,6 +2163,7 @@ extern const u32		sched_prio_to_wmult[40
 #else
 #define ENQUEUE_MIGRATED	0x00
 #endif
+#define ENQUEUE_INITIAL		0x80
 
 #define RETRY_TASK		((void *)-1UL)