With cache-aware scheduling enabled, each task is assigned a
preferred LLC ID. This allows quick identification of the LLC domain
where the task prefers to run, similar to numa_preferred_nid in
NUMA balancing.

Co-developed-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
---

Notes:
    v3->v4:
        Use WRITE_ONCE()/READ_ONCE() on p->preferred_llc
        (Madadi Vineeth Reddy)

 include/linux/sched.h |  1 +
 init/init_task.c      |  3 +++
 kernel/sched/fair.c   | 43 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 47 insertions(+)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index bd33f5b9096b..526108acc483 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1408,6 +1408,7 @@ struct task_struct {
 
 #ifdef CONFIG_SCHED_CACHE
 	struct callback_head		cache_work;
+	int				preferred_llc;
 #endif
 
 	struct rseq_data		rseq;
diff --git a/init/init_task.c b/init/init_task.c
index 5c838757fc10..9f964898d40e 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -214,6 +214,9 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
 	.numa_group	= NULL,
 	.numa_faults	= NULL,
 #endif
+#ifdef CONFIG_SCHED_CACHE
+	.preferred_llc  = -1,
+#endif
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	.kasan_depth	= 1,
 #endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6244443ecdc0..1eda689e0136 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1366,11 +1366,43 @@ static unsigned long fraction_mm_sched(struct rq *rq,
 	return div64_u64(NICE_0_LOAD * pcpu_sched->runtime, rq->cpu_runtime + 1);
 }
 
+static int get_pref_llc(struct task_struct *p, struct mm_struct *mm)
+{
+	int mm_sched_llc = -1;
+
+	if (!mm)
+		return -1;
+
+	if (mm->sc_stat.cpu != -1) {
+		mm_sched_llc = llc_id(mm->sc_stat.cpu);
+
+#ifdef CONFIG_NUMA_BALANCING
+		/*
+		 * Don't assign preferred LLC if it
+		 * conflicts with NUMA balancing.
+		 * This can happen when sched_setnuma() gets
+		 * called, however it is not much of an issue
+		 * because we expect account_mm_sched() to get
+		 * called fairly regularly -- at a higher rate
+		 * than sched_setnuma() at least -- and thus the
+		 * conflict only exists for a short period of time.
+		 */
+		if (static_branch_likely(&sched_numa_balancing) &&
+		    p->numa_preferred_nid >= 0 &&
+		    cpu_to_node(mm->sc_stat.cpu) != p->numa_preferred_nid)
+			mm_sched_llc = -1;
+#endif
+	}
+
+	return mm_sched_llc;
+}
+
 static inline
 void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec)
 {
 	struct sched_cache_time *pcpu_sched;
 	struct mm_struct *mm = p->mm;
+	int mm_sched_llc = -1;
 	unsigned long epoch;
 
 	if (!sched_cache_enabled())
@@ -1404,6 +1436,11 @@ void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec)
 		if (mm->sc_stat.cpu != -1)
 			mm->sc_stat.cpu = -1;
 	}
+
+	mm_sched_llc = get_pref_llc(p, mm);
+
+	if (READ_ONCE(p->preferred_llc) != mm_sched_llc)
+		WRITE_ONCE(p->preferred_llc, mm_sched_llc);
 }
 
 static void task_tick_cache(struct rq *rq, struct task_struct *p)
@@ -1577,6 +1614,12 @@ void init_sched_mm(struct task_struct *p) { }
 
 static void task_tick_cache(struct rq *rq, struct task_struct *p) { }
 
+static inline int get_pref_llc(struct task_struct *p,
+			       struct mm_struct *mm)
+{
+	return -1;
+}
+
 #endif /* CONFIG_SCHED_CACHE */
 
 /*
-- 
2.32.0