[PATCH 07/19] sched/fair: Track LLC-preferred tasks per runqueue

[Tim Chen <tim.c.chen@linux.intel.com>]

For each runqueue, track the number of tasks with an LLC preference
and how many of them are running on their preferred LLC. This mirrors
nr_numa_running and nr_preferred_running for NUMA balancing, and will
be used by cache-aware load balancing in later patches.

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
---
 kernel/sched/core.c  | 12 +++++++++++
 kernel/sched/fair.c  | 47 +++++++++++++++++++++++++++++++++++++++++++-
 kernel/sched/sched.h |  7 +++++++
 3 files changed, 65 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 79d15e904d12..5940756e2da3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -529,6 +529,18 @@ void __trace_set_current_state(int state_value)
 }
 EXPORT_SYMBOL(__trace_set_current_state);
 
+#ifdef CONFIG_SMP
+int task_llc(const struct task_struct *p)
+{
+	return per_cpu(sd_llc_id, task_cpu(p));
+}
+#else
+int task_llc(const struct task_struct *p)
+{
+	return 0;
+}
+#endif
+
 /*
  * Serialization rules:
  *
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d6167a029c47..fd315937c0cf 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1235,6 +1235,24 @@ static inline int llc_idx(int cpu)
 	return per_cpu(sd_llc_idx, cpu);
 }
 
+static void account_llc_enqueue(struct rq *rq, struct task_struct *p)
+{
+	if (!sched_cache_enabled())
+		return;
+
+	rq->nr_llc_running += (p->preferred_llc != -1);
+	rq->nr_pref_llc_running += (p->preferred_llc == task_llc(p));
+}
+
+static void account_llc_dequeue(struct rq *rq, struct task_struct *p)
+{
+	if (!sched_cache_enabled())
+		return;
+
+	rq->nr_llc_running -= (p->preferred_llc != -1);
+	rq->nr_pref_llc_running -= (p->preferred_llc == task_llc(p));
+}
+
 void mm_init_sched(struct mm_struct *mm, struct mm_sched __percpu *_pcpu_sched)
 {
 	unsigned long epoch;
@@ -1306,6 +1324,8 @@ static unsigned long __no_profile fraction_mm_sched(struct rq *rq, struct mm_sch
 	return div64_u64(NICE_0_LOAD * pcpu_sched->runtime, rq->cpu_runtime + 1);
 }
 
+static unsigned int task_running_on_cpu(int cpu, struct task_struct *p);
+
 static inline
 void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec)
 {
@@ -1347,8 +1367,13 @@ void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec)
 	if (mm->mm_sched_cpu != -1)
 		mm_sched_llc = per_cpu(sd_llc_id, mm->mm_sched_cpu);
 
-	if (p->preferred_llc != mm_sched_llc)
+	/* task not on rq accounted later in account_entity_enqueue() */
+	if (task_running_on_cpu(rq->cpu, p) &&
+	    p->preferred_llc != mm_sched_llc) {
+		account_llc_dequeue(rq, p);
 		p->preferred_llc = mm_sched_llc;
+		account_llc_enqueue(rq, p);
+	}
 }
 
 static void task_tick_cache(struct rq *rq, struct task_struct *p)
@@ -1497,6 +1522,15 @@ void init_sched_mm(struct task_struct *p)
 	work->next = work;
 }
 
+void reset_llc_stats(struct rq *rq)
+{
+	if (!sched_cache_enabled())
+		return;
+
+	rq->nr_llc_running = 0;
+	rq->nr_pref_llc_running = 0;
+}
+
 #else
 
 static inline void account_mm_sched(struct rq *rq, struct task_struct *p,
@@ -1506,6 +1540,11 @@ void init_sched_mm(struct task_struct *p) { }
 
 static void task_tick_cache(struct rq *rq, struct task_struct *p) { }
 
+static void account_llc_enqueue(struct rq *rq, struct task_struct *p) {}
+
+static void account_llc_dequeue(struct rq *rq, struct task_struct *p) {}
+
+void reset_llc_stats(struct rq *rq) {}
 #endif
 
 /*
@@ -3999,6 +4038,7 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		struct rq *rq = rq_of(cfs_rq);
 
 		account_numa_enqueue(rq, task_of(se));
+		account_llc_enqueue(rq, task_of(se));
 		list_add(&se->group_node, &rq->cfs_tasks);
 	}
 	cfs_rq->nr_queued++;
@@ -4010,9 +4050,14 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	update_load_sub(&cfs_rq->load, se->load.weight);
 	if (entity_is_task(se)) {
 		account_numa_dequeue(rq_of(cfs_rq), task_of(se));
+		account_llc_dequeue(rq_of(cfs_rq), task_of(se));
 		list_del_init(&se->group_node);
 	}
 	cfs_rq->nr_queued--;
+
+	/* safeguard to clear the cache aware data */
+	if (!parent_entity(se) && !cfs_rq->nr_queued)
+		reset_llc_stats(rq_of(cfs_rq));
 }
 
 /*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b448ad6dc51d..3ab64067acc6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1098,6 +1098,10 @@ struct rq {
 	unsigned int		nr_preferred_running;
 	unsigned int		numa_migrate_on;
 #endif
+#ifdef CONFIG_SCHED_CACHE
+	unsigned int		nr_pref_llc_running;
+	unsigned int		nr_llc_running;
+#endif
 #ifdef CONFIG_NO_HZ_COMMON
 	unsigned long		last_blocked_load_update_tick;
 	unsigned int		has_blocked_load;
@@ -1952,6 +1956,9 @@ init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
 
 #endif /* !CONFIG_NUMA_BALANCING */
 
+void reset_llc_stats(struct rq *rq);
+int task_llc(const struct task_struct *p);
+
 static inline void
 queue_balance_callback(struct rq *rq,
 		       struct balance_callback *head,
-- 
2.32.0