sched: fair: weight calculations

In order to level the hierarchy, we need to calculate load based on the
root view. That is, each task's load is in the same unit.

             A
            / \
           B   1
          / \
         2   3

To compute 1's load we do:

	   weight(1)
	--------------
	 rq_weight(A)

To compute 2's load we do:

	  weight(2)      weight(B)
	------------ * -----------
	rq_weight(B)   rw_weight(A)

This yields load fractions in comparable units.

The consequence is that it changes virtual time. We used to have:

                time_{i}
  vtime_{i} = ------------
               weight_{i}

  vtime = \Sum vtime_{i} = time / rq_weight.

But with the new way of load calculation we get that vtime equals time.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

2 files changed, 65 insertions, 39 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 3202462109f5..6d55dfc56cab 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1320,6 +1320,9 @@ static void __resched_task(struct task_struct *p, int tif_bit)
  */
 #define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
 
+/*
+ * delta *= weight / lw
+ */
 static unsigned long
 calc_delta_mine(unsigned long delta_exec, unsigned long weight,
 		struct load_weight *lw)
@@ -1342,12 +1345,6 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
 	return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
 }
 
-static inline unsigned long
-calc_delta_fair(unsigned long delta_exec, struct load_weight *lw)
-{
-	return calc_delta_mine(delta_exec, NICE_0_LOAD, lw);
-}
-
 static inline void update_load_add(struct load_weight *lw, unsigned long inc)
 {
 	lw->weight += inc;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index ed8ce329899b..d72e8b41b3e4 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -334,6 +334,34 @@ int sched_nr_latency_handler(struct ctl_table *table, int write,
 #endif
 
 /*
+ * delta *= w / rw
+ */
+static inline unsigned long
+calc_delta_weight(unsigned long delta, struct sched_entity *se)
+{
+	for_each_sched_entity(se) {
+		delta = calc_delta_mine(delta,
+				se->load.weight, &cfs_rq_of(se)->load);
+	}
+
+	return delta;
+}
+
+/*
+ * delta *= rw / w
+ */
+static inline unsigned long
+calc_delta_fair(unsigned long delta, struct sched_entity *se)
+{
+	for_each_sched_entity(se) {
+		delta = calc_delta_mine(delta,
+				cfs_rq_of(se)->load.weight, &se->load);
+	}
+
+	return delta;
+}
+
+/*
  * The idea is to set a period in which each task runs once.
  *
  * When there are too many tasks (sysctl_sched_nr_latency) we have to stretch
@@ -362,47 +390,54 @@ static u64 __sched_period(unsigned long nr_running)
  */
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u64 slice = __sched_period(cfs_rq->nr_running);
-
-	for_each_sched_entity(se) {
-		cfs_rq = cfs_rq_of(se);
-
-		slice *= se->load.weight;
-		do_div(slice, cfs_rq->load.weight);
-	}
-
-
-	return slice;
+	return calc_delta_weight(__sched_period(cfs_rq->nr_running), se);
 }
 
 /*
  * We calculate the vruntime slice of a to be inserted task
  *
- * vs = s/w = p/rw
+ * vs = s*rw/w = p
  */
 static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	unsigned long nr_running = cfs_rq->nr_running;
-	unsigned long weight;
-	u64 vslice;
 
 	if (!se->on_rq)
 		nr_running++;
 
-	vslice = __sched_period(nr_running);
+	return __sched_period(nr_running);
+}
+
+/*
+ * The goal of calc_delta_asym() is to be asymmetrically around NICE_0_LOAD, in
+ * that it favours >=0 over <0.
+ *
+ *   -20         |
+ *               |
+ *     0 --------+-------
+ *             .'
+ *    19     .'
+ *
+ */
+static unsigned long
+calc_delta_asym(unsigned long delta, struct sched_entity *se)
+{
+	struct load_weight lw = {
+		.weight = NICE_0_LOAD,
+		.inv_weight = 1UL << (WMULT_SHIFT-NICE_0_SHIFT)
+	};
 
 	for_each_sched_entity(se) {
-		cfs_rq = cfs_rq_of(se);
+		struct load_weight *se_lw = &se->load;
 
-		weight = cfs_rq->load.weight;
-		if (!se->on_rq)
-			weight += se->load.weight;
+		if (se->load.weight < NICE_0_LOAD)
+			se_lw = &lw;
 
-		vslice *= NICE_0_LOAD;
-		do_div(vslice, weight);
+		delta = calc_delta_mine(delta,
+				cfs_rq_of(se)->load.weight, se_lw);
 	}
 
-	return vslice;
+	return delta;
 }
 
 /*
@@ -419,11 +454,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 
 	curr->sum_exec_runtime += delta_exec;
 	schedstat_add(cfs_rq, exec_clock, delta_exec);
-	delta_exec_weighted = delta_exec;
-	if (unlikely(curr->load.weight != NICE_0_LOAD)) {
-		delta_exec_weighted = calc_delta_fair(delta_exec_weighted,
-							&curr->load);
-	}
+	delta_exec_weighted = calc_delta_fair(delta_exec, curr);
 	curr->vruntime += delta_exec_weighted;
 }
 
@@ -632,8 +663,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 		/* sleeps upto a single latency don't count. */
 		if (sched_feat(NEW_FAIR_SLEEPERS)) {
 			if (sched_feat(NORMALIZED_SLEEPER))
-				vruntime -= calc_delta_fair(sysctl_sched_latency,
-						&cfs_rq->load);
+				vruntime -= calc_delta_weight(sysctl_sched_latency, se);
 			else
 				vruntime -= sysctl_sched_latency;
 		}
@@ -1132,11 +1162,10 @@ static unsigned long wakeup_gran(struct sched_entity *se)
 	unsigned long gran = sysctl_sched_wakeup_granularity;
 
 	/*
-	 * More easily preempt - nice tasks, while not making
-	 * it harder for + nice tasks.
+	 * More easily preempt - nice tasks, while not making it harder for
+	 * + nice tasks.
 	 */
-	if (unlikely(se->load.weight > NICE_0_LOAD))
-		gran = calc_delta_fair(gran, &se->load);
+	gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se);
 
 	return gran;
 }