[PATCH 1/4] sched/cache: Keep nr_pref_llc_running in the runnable domain

[Tim Chen]

alb_break_llc() decides whether to break LLC preference during active
load balance. It does so by testing that every runnable fair task on the
source rq prefers its LLC:

	env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable

But the two counters cover different sets. nr_pref_llc_running is updated
in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued,
so it follows queued tasks. h_nr_runnable is updated in set_delayed()/
clear_delayed() and drops delay-dequeued tasks.

So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted
in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks,
alb_break_llc() returns false, and active balance is free to pull a task
off its preferred LLC. Active balance only moves runnable tasks, and this
is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB
skips the per-task test in can_migrate_task(). The runnable set is the one
we want.

Fix it on the counter side. A task should be counted in
nr_pref_llc_running exactly while it is both queued on its preferred LLC
(pref_llc_queued) and runnable (!sched_delayed). Define that membership
once in task_pref_llc_runnable(), and adjust the counter only through
pref_llc_running_inc()/pref_llc_running_dec() from the four sites that
change either input: account_llc_enqueue(), account_llc_dequeue(),
set_delayed() and clear_delayed(). Gating every update on the same
predicate keeps the delay, wake and dequeue paths from double-counting
or underflowing; see the comments at those sites for the ordering.

nr_llc_running and sd->llc_counts are not touched and stay on queued
semantics.

Reported-by: Zhan Xusheng <zhanxusheng@xxxxxxxxxx>
Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xxxxxxxxxx/
Suggested-by: Chen Yu <yu.c.chen@xxxxxxxxx>
Signed-off-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
---
 kernel/sched/fair.c | 52 +++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 50 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d5989b53adef..b1ef013b0342 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1551,6 +1551,28 @@ static bool invalid_llc_nr(struct mm_struct *mm, struct task_struct *p,
 			(scale * per_cpu(sd_llc_size, cpu)));
 }
 
+/*
+ * A task counts in nr_pref_llc_running while it is queued on its preferred
+ * LLC (pref_llc_queued) and runnable (!sched_delayed), keeping the counter in
+ * the runnable domain so alb_break_llc() can compare it with h_nr_runnable.
+ */
+static bool task_pref_llc_runnable(struct task_struct *p)
+{
+	return p->pref_llc_queued && !p->se.sched_delayed;
+}
+
+static void pref_llc_running_inc(struct rq *rq, struct task_struct *p)
+{
+	if (task_pref_llc_runnable(p))
+		rq->nr_pref_llc_running++;
+}
+
+static void pref_llc_running_dec(struct rq *rq, struct task_struct *p)
+{
+	if (task_pref_llc_runnable(p))
+		rq->nr_pref_llc_running--;
+}
+
 static void account_llc_enqueue(struct rq *rq, struct task_struct *p)
 {
 	int pref_llc, pref_llc_queued;
@@ -1562,7 +1584,6 @@ static void account_llc_enqueue(struct rq *rq, struct task_struct *p)
 
 	pref_llc_queued = (pref_llc == task_llc(p));
 	rq->nr_llc_running++;
-	rq->nr_pref_llc_running += pref_llc_queued;
 
 	/*
 	 * Record whether p is enqueued on its preferred
@@ -1580,6 +1601,9 @@ static void account_llc_enqueue(struct rq *rq, struct task_struct *p)
 	 */
 	p->pref_llc_queued = pref_llc_queued;
 
+	/* Skipped while delayed; clear_delayed() adds it back on wake. */
+	pref_llc_running_inc(rq, p);
+
 	sd = rcu_dereference_all(rq->sd);
 	if (sd && (unsigned int)pref_llc < sd->llc_max)
 		sd->llc_counts[pref_llc]++;
@@ -1596,7 +1620,12 @@ static void account_llc_dequeue(struct rq *rq, struct task_struct *p)
 
 	rq->nr_llc_running--;
 	if (p->pref_llc_queued) {
-		rq->nr_pref_llc_running--;
+		/*
+		 * Skipped if still delayed (set_delayed() already removed it);
+		 * clearing pref_llc_queued below also stops clear_delayed()
+		 * from re-adding it.
+		 */
+		pref_llc_running_dec(rq, p);
 		/*
 		 * Update the status in case
 		 * other logic might query
@@ -2021,6 +2050,10 @@ static void account_llc_enqueue(struct rq *rq, struct task_struct *p) {}
 
 static void account_llc_dequeue(struct rq *rq, struct task_struct *p) {}
 
+static void pref_llc_running_inc(struct rq *rq, struct task_struct *p) {}
+
+static void pref_llc_running_dec(struct rq *rq, struct task_struct *p) {}
+
 #endif /* CONFIG_SCHED_CACHE */
 
 /*
@@ -6395,6 +6428,14 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
 
 static void set_delayed(struct sched_entity *se)
 {
+	/*
+	 * Drop a task leaving the runnable set. Must run before sched_delayed
+	 * is set, or task_pref_llc_runnable() would already exclude it;
+	 * clear_delayed() mirrors this after clearing the flag.
+	 */
+	if (entity_is_task(se))
+		pref_llc_running_dec(rq_of(cfs_rq_of(se)), task_of(se));
+
 	se->sched_delayed = 1;
 
 	/*
@@ -6425,6 +6466,13 @@ static void clear_delayed(struct sched_entity *se)
 	if (!entity_is_task(se))
 		return;
 
+	/*
+	 * Re-add on wake, after sched_delayed is cleared. On a final delayed
+	 * dequeue account_llc_dequeue() already cleared pref_llc_queued, so
+	 * this does nothing.
+	 */
+	pref_llc_running_inc(rq_of(cfs_rq_of(se)), task_of(se));
+
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
-- 
2.32.0