[Patch v4 07/22] sched/cache: Track LLC-preferred tasks per runqueue

[Tim Chen]

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.

Co-developed-by: Chen Yu <yu.c.chen@xxxxxxxxx>
Signed-off-by: Chen Yu <yu.c.chen@xxxxxxxxx>
Signed-off-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
---

Notes:
    v3->v4:
        Use READ_ONCE() to access p->preferred_llc
        (Madadi Vineeth Reddy).

 kernel/sched/core.c  |  5 +++++
 kernel/sched/fair.c  | 47 +++++++++++++++++++++++++++++++++++++++++---
 kernel/sched/sched.h |  8 ++++++++
 3 files changed, 57 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1188b5d24933..93a1dbc02667 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -539,6 +539,11 @@ void __trace_set_current_state(int state_value)
 }
 EXPORT_SYMBOL(__trace_set_current_state);
 
+int task_llc(const struct task_struct *p)
+{
+	return per_cpu(sd_llc_id, task_cpu(p));
+}
+
 /*
  * Serialization rules:
  *
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1eda689e0136..4b760bd604e7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1291,6 +1291,30 @@ static int llc_id(int cpu)
 	return per_cpu(sd_llc_id, cpu);
 }
 
+static void account_llc_enqueue(struct rq *rq, struct task_struct *p)
+{
+	int pref_llc;
+
+	pref_llc = p->preferred_llc;
+	if (pref_llc < 0)
+		return;
+
+	rq->nr_llc_running++;
+	rq->nr_pref_llc_running += (pref_llc == task_llc(p));
+}
+
+static void account_llc_dequeue(struct rq *rq, struct task_struct *p)
+{
+	int pref_llc;
+
+	pref_llc = p->preferred_llc;
+	if (pref_llc < 0)
+		return;
+
+	rq->nr_llc_running--;
+	rq->nr_pref_llc_running -= (pref_llc == task_llc(p));
+}
+
 void mm_init_sched(struct mm_struct *mm,
 		   struct sched_cache_time __percpu *_pcpu_sched)
 {
@@ -1397,6 +1421,8 @@ static int get_pref_llc(struct task_struct *p, struct mm_struct *mm)
 	return mm_sched_llc;
 }
 
+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)
 {
@@ -1439,8 +1465,13 @@ void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec)
 
 	mm_sched_llc = get_pref_llc(p, mm);
 
-	if (READ_ONCE(p->preferred_llc) != mm_sched_llc)
+	/* task not on rq accounted later in account_entity_enqueue() */
+	if (task_running_on_cpu(rq->cpu, p) &&
+	    READ_ONCE(p->preferred_llc) != mm_sched_llc) {
+		account_llc_dequeue(rq, p);
 		WRITE_ONCE(p->preferred_llc, mm_sched_llc);
+		account_llc_enqueue(rq, p);
+	}
 }
 
 static void task_tick_cache(struct rq *rq, struct task_struct *p)
@@ -1620,6 +1651,10 @@ static inline int get_pref_llc(struct task_struct *p,
 	return -1;
 }
 
+static void account_llc_enqueue(struct rq *rq, struct task_struct *p) {}
+
+static void account_llc_dequeue(struct rq *rq, struct task_struct *p) {}
+
 #endif /* CONFIG_SCHED_CACHE */
 
 /*
@@ -4106,9 +4141,11 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	update_load_add(&cfs_rq->load, se->load.weight);
 	if (entity_is_task(se)) {
+		struct task_struct *p = task_of(se);
 		struct rq *rq = rq_of(cfs_rq);
 
-		account_numa_enqueue(rq, task_of(se));
+		account_numa_enqueue(rq, p);
+		account_llc_enqueue(rq, p);
 		list_add(&se->group_node, &rq->cfs_tasks);
 	}
 	cfs_rq->nr_queued++;
@@ -4119,7 +4156,11 @@ 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));
+		struct task_struct *p = task_of(se);
+		struct rq *rq = rq_of(cfs_rq);
+
+		account_numa_dequeue(rq, p);
+		account_llc_dequeue(rq, p);
 		list_del_init(&se->group_node);
 	}
 	cfs_rq->nr_queued--;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9defeeeb3e8e..081f23a48414 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1195,6 +1195,12 @@ struct rq {
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int		numa_migrate_on;
 #endif
+
+#ifdef CONFIG_SCHED_CACHE
+	unsigned int		nr_pref_llc_running;
+	unsigned int		nr_llc_running;
+#endif
+
 	/*
 	 * This is part of a global counter where only the total sum
 	 * over all CPUs matters. A task can increase this counter on
@@ -2066,6 +2072,8 @@ init_numa_balancing(u64 clone_flags, struct task_struct *p)
 
 #endif /* !CONFIG_NUMA_BALANCING */
 
+int task_llc(const struct task_struct *p);
+
 static inline void
 queue_balance_callback(struct rq *rq,
 		       struct balance_callback *head,
-- 
2.32.0