sched: de-SCHED_OTHER-ize the RT path

The current wake-up code path tries to determine if it can optimize the
wake-up to "this_cpu" by computing load calculations.  The problem is that
these calculations are only relevant to SCHED_OTHER tasks where load is king.
For RT tasks, priority is king.  So the load calculation is completely wasted
bandwidth.

Therefore, we create a new sched_class interface to help with
pre-wakeup routing decisions and move the load calculation as a function
of CFS task's class.

Signed-off-by: Gregory Haskins <ghaskins@novell.com>
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

5 files changed, 195 insertions, 140 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b07a2cf..6fbbf38 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -827,6 +827,7 @@ struct sched_class {
 	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup);
 	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
 	void (*yield_task) (struct rq *rq);
+	int  (*select_task_rq)(struct task_struct *p, int sync);
 
 	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p);
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 66e99b4..3344ba7 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -960,6 +960,13 @@ static inline void dec_cpu_load(struct rq *rq, unsigned long load)
 	update_load_sub(&rq->load, load);
 }
 
+#ifdef CONFIG_SMP
+static unsigned long source_load(int cpu, int type);
+static unsigned long target_load(int cpu, int type);
+static unsigned long cpu_avg_load_per_task(int cpu);
+static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
+#endif /* CONFIG_SMP */
+
 #include "sched_stats.h"
 #include "sched_idletask.c"
 #include "sched_fair.c"
@@ -1118,7 +1125,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 /*
  * Is this task likely cache-hot:
  */
-static inline int
+static int
 task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
 {
 	s64 delta;
@@ -1343,7 +1350,7 @@ static unsigned long target_load(int cpu, int type)
 /*
  * Return the average load per task on the cpu's run queue
  */
-static inline unsigned long cpu_avg_load_per_task(int cpu)
+static unsigned long cpu_avg_load_per_task(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long total = weighted_cpuload(cpu);
@@ -1500,58 +1507,6 @@ static int sched_balance_self(int cpu, int flag)
 
 #endif /* CONFIG_SMP */
 
-/*
- * wake_idle() will wake a task on an idle cpu if task->cpu is
- * not idle and an idle cpu is available.  The span of cpus to
- * search starts with cpus closest then further out as needed,
- * so we always favor a closer, idle cpu.
- *
- * Returns the CPU we should wake onto.
- */
-#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
-static int wake_idle(int cpu, struct task_struct *p)
-{
-	cpumask_t tmp;
-	struct sched_domain *sd;
-	int i;
-
-	/*
-	 * If it is idle, then it is the best cpu to run this task.
-	 *
-	 * This cpu is also the best, if it has more than one task already.
-	 * Siblings must be also busy(in most cases) as they didn't already
-	 * pickup the extra load from this cpu and hence we need not check
-	 * sibling runqueue info. This will avoid the checks and cache miss
-	 * penalities associated with that.
-	 */
-	if (idle_cpu(cpu) || cpu_rq(cpu)->nr_running > 1)
-		return cpu;
-
-	for_each_domain(cpu, sd) {
-		if (sd->flags & SD_WAKE_IDLE) {
-			cpus_and(tmp, sd->span, p->cpus_allowed);
-			for_each_cpu_mask(i, tmp) {
-				if (idle_cpu(i)) {
-					if (i != task_cpu(p)) {
-						schedstat_inc(p,
-							se.nr_wakeups_idle);
-					}
-					return i;
-				}
-			}
-		} else {
-			break;
-		}
-	}
-	return cpu;
-}
-#else
-static inline int wake_idle(int cpu, struct task_struct *p)
-{
-	return cpu;
-}
-#endif
-
 /***
  * try_to_wake_up - wake up a thread
  * @p: the to-be-woken-up thread
@@ -1573,8 +1528,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 	long old_state;
 	struct rq *rq;
 #ifdef CONFIG_SMP
-	struct sched_domain *sd, *this_sd = NULL;
-	unsigned long load, this_load;
 	int new_cpu;
 #endif
 
@@ -1594,90 +1547,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 	if (unlikely(task_running(rq, p)))
 		goto out_activate;
 
-	new_cpu = cpu;
-
-	schedstat_inc(rq, ttwu_count);
-	if (cpu == this_cpu) {
-		schedstat_inc(rq, ttwu_local);
-		goto out_set_cpu;
-	}
-
-	for_each_domain(this_cpu, sd) {
-		if (cpu_isset(cpu, sd->span)) {
-			schedstat_inc(sd, ttwu_wake_remote);
-			this_sd = sd;
-			break;
-		}
-	}
-
-	if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
-		goto out_set_cpu;
-
-	/*
-	 * Check for affine wakeup and passive balancing possibilities.
-	 */
-	if (this_sd) {
-		int idx = this_sd->wake_idx;
-		unsigned int imbalance;
-
-		imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
-
-		load = source_load(cpu, idx);
-		this_load = target_load(this_cpu, idx);
-
-		new_cpu = this_cpu; /* Wake to this CPU if we can */
-
-		if (this_sd->flags & SD_WAKE_AFFINE) {
-			unsigned long tl = this_load;
-			unsigned long tl_per_task;
-
-			/*
-			 * Attract cache-cold tasks on sync wakeups:
-			 */
-			if (sync && !task_hot(p, rq->clock, this_sd))
-				goto out_set_cpu;
-
-			schedstat_inc(p, se.nr_wakeups_affine_attempts);
-			tl_per_task = cpu_avg_load_per_task(this_cpu);
-
-			/*
-			 * If sync wakeup then subtract the (maximum possible)
-			 * effect of the currently running task from the load
-			 * of the current CPU:
-			 */
-			if (sync)
-				tl -= current->se.load.weight;
-
-			if ((tl <= load &&
-				tl + target_load(cpu, idx) <= tl_per_task) ||
-			       100*(tl + p->se.load.weight) <= imbalance*load) {
-				/*
-				 * This domain has SD_WAKE_AFFINE and
-				 * p is cache cold in this domain, and
-				 * there is no bad imbalance.
-				 */
-				schedstat_inc(this_sd, ttwu_move_affine);
-				schedstat_inc(p, se.nr_wakeups_affine);
-				goto out_set_cpu;
-			}
-		}
-
-		/*
-		 * Start passive balancing when half the imbalance_pct
-		 * limit is reached.
-		 */
-		if (this_sd->flags & SD_WAKE_BALANCE) {
-			if (imbalance*this_load <= 100*load) {
-				schedstat_inc(this_sd, ttwu_move_balance);
-				schedstat_inc(p, se.nr_wakeups_passive);
-				goto out_set_cpu;
-			}
-		}
-	}
-
-	new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
-out_set_cpu:
-	new_cpu = wake_idle(new_cpu, p);
+	new_cpu = p->sched_class->select_task_rq(p, sync);
 	if (new_cpu != cpu) {
 		set_task_cpu(p, new_cpu);
 		task_rq_unlock(rq, &flags);
@@ -1693,6 +1563,23 @@ out_set_cpu:
 		cpu = task_cpu(p);
 	}
 
+#ifdef CONFIG_SCHEDSTATS
+	schedstat_inc(rq, ttwu_count);
+	if (cpu == this_cpu)
+		schedstat_inc(rq, ttwu_local);
+	else {
+		struct sched_domain *sd;
+		for_each_domain(this_cpu, sd) {
+			if (cpu_isset(cpu, sd->span)) {
+				schedstat_inc(sd, ttwu_wake_remote);
+				break;
+			}
+		}
+	}
+
+#endif
+
+
 out_activate:
 #endif /* CONFIG_SMP */
 	schedstat_inc(p, se.nr_wakeups);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5c208e0..f881fc5 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -861,6 +861,151 @@ static void yield_task_fair(struct rq *rq)
 }
 
 /*
+ * wake_idle() will wake a task on an idle cpu if task->cpu is
+ * not idle and an idle cpu is available.  The span of cpus to
+ * search starts with cpus closest then further out as needed,
+ * so we always favor a closer, idle cpu.
+ *
+ * Returns the CPU we should wake onto.
+ */
+#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
+static int wake_idle(int cpu, struct task_struct *p)
+{
+	cpumask_t tmp;
+	struct sched_domain *sd;
+	int i;
+
+	/*
+	 * If it is idle, then it is the best cpu to run this task.
+	 *
+	 * This cpu is also the best, if it has more than one task already.
+	 * Siblings must be also busy(in most cases) as they didn't already
+	 * pickup the extra load from this cpu and hence we need not check
+	 * sibling runqueue info. This will avoid the checks and cache miss
+	 * penalities associated with that.
+	 */
+	if (idle_cpu(cpu) || cpu_rq(cpu)->nr_running > 1)
+		return cpu;
+
+	for_each_domain(cpu, sd) {
+		if (sd->flags & SD_WAKE_IDLE) {
+			cpus_and(tmp, sd->span, p->cpus_allowed);
+			for_each_cpu_mask(i, tmp) {
+				if (idle_cpu(i)) {
+					if (i != task_cpu(p)) {
+						schedstat_inc(p,
+						       se.nr_wakeups_idle);
+					}
+					return i;
+				}
+			}
+		} else {
+			break;
+		}
+	}
+	return cpu;
+}
+#else
+static inline int wake_idle(int cpu, struct task_struct *p)
+{
+	return cpu;
+}
+#endif
+
+#ifdef CONFIG_SMP
+static int select_task_rq_fair(struct task_struct *p, int sync)
+{
+	int cpu, this_cpu;
+	struct rq *rq;
+	struct sched_domain *sd, *this_sd = NULL;
+	int new_cpu;
+
+	cpu      = task_cpu(p);
+	rq       = task_rq(p);
+	this_cpu = smp_processor_id();
+	new_cpu  = cpu;
+
+	for_each_domain(this_cpu, sd) {
+		if (cpu_isset(cpu, sd->span)) {
+			this_sd = sd;
+			break;
+		}
+	}
+
+	if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
+		goto out_set_cpu;
+
+	/*
+	 * Check for affine wakeup and passive balancing possibilities.
+	 */
+	if (this_sd) {
+		int idx = this_sd->wake_idx;
+		unsigned int imbalance;
+		unsigned long load, this_load;
+
+		imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
+
+		load = source_load(cpu, idx);
+		this_load = target_load(this_cpu, idx);
+
+		new_cpu = this_cpu; /* Wake to this CPU if we can */
+
+		if (this_sd->flags & SD_WAKE_AFFINE) {
+			unsigned long tl = this_load;
+			unsigned long tl_per_task;
+
+			/*
+			 * Attract cache-cold tasks on sync wakeups:
+			 */
+			if (sync && !task_hot(p, rq->clock, this_sd))
+				goto out_set_cpu;
+
+			schedstat_inc(p, se.nr_wakeups_affine_attempts);
+			tl_per_task = cpu_avg_load_per_task(this_cpu);
+
+			/*
+			 * If sync wakeup then subtract the (maximum possible)
+			 * effect of the currently running task from the load
+			 * of the current CPU:
+			 */
+			if (sync)
+				tl -= current->se.load.weight;
+
+			if ((tl <= load &&
+				tl + target_load(cpu, idx) <= tl_per_task) ||
+			       100*(tl + p->se.load.weight) <= imbalance*load) {
+				/*
+				 * This domain has SD_WAKE_AFFINE and
+				 * p is cache cold in this domain, and
+				 * there is no bad imbalance.
+				 */
+				schedstat_inc(this_sd, ttwu_move_affine);
+				schedstat_inc(p, se.nr_wakeups_affine);
+				goto out_set_cpu;
+			}
+		}
+
+		/*
+		 * Start passive balancing when half the imbalance_pct
+		 * limit is reached.
+		 */
+		if (this_sd->flags & SD_WAKE_BALANCE) {
+			if (imbalance*this_load <= 100*load) {
+				schedstat_inc(this_sd, ttwu_move_balance);
+				schedstat_inc(p, se.nr_wakeups_passive);
+				goto out_set_cpu;
+			}
+		}
+	}
+
+	new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
+out_set_cpu:
+	return wake_idle(new_cpu, p);
+}
+#endif /* CONFIG_SMP */
+
+
+/*
  * Preempt the current task with a newly woken task if needed:
  */
 static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
@@ -1153,6 +1298,9 @@ static const struct sched_class fair_sched_class = {
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
+#ifdef CONFIG_SMP
+	.select_task_rq		= select_task_rq_fair,
+#endif /* CONFIG_SMP */
 
 	.check_preempt_curr	= check_preempt_wakeup,
 
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index bf9c25c..ca53748 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -5,6 +5,12 @@
  *  handled in sched_fair.c)
  */
 
+#ifdef CONFIG_SMP
+static int select_task_rq_idle(struct task_struct *p, int sync)
+{
+	return task_cpu(p); /* IDLE tasks as never migrated */
+}
+#endif /* CONFIG_SMP */
 /*
  * Idle tasks are unconditionally rescheduled:
  */
@@ -72,6 +78,9 @@ const struct sched_class idle_sched_class = {
 
 	/* dequeue is not valid, we print a debug message there: */
 	.dequeue_task		= dequeue_task_idle,
+#ifdef CONFIG_SMP
+	.select_task_rq		= select_task_rq_idle,
+#endif /* CONFIG_SMP */
 
 	.check_preempt_curr	= check_preempt_curr_idle,
 
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index b788e35..5de1aeb 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -150,6 +150,13 @@ yield_task_rt(struct rq *rq)
 	requeue_task_rt(rq, rq->curr);
 }
 
+#ifdef CONFIG_SMP
+static int select_task_rq_rt(struct task_struct *p, int sync)
+{
+	return task_cpu(p);
+}
+#endif /* CONFIG_SMP */
+
 /*
  * Preempt the current task with a newly woken task if needed:
  */
@@ -667,6 +674,9 @@ const struct sched_class rt_sched_class = {
 	.enqueue_task		= enqueue_task_rt,
 	.dequeue_task		= dequeue_task_rt,
 	.yield_task		= yield_task_rt,
+#ifdef CONFIG_SMP
+	.select_task_rq		= select_task_rq_rt,
+#endif /* CONFIG_SMP */
 
 	.check_preempt_curr	= check_preempt_curr_rt,