[PATCH 03/17] sched: Make NOHZ CFS bandwidth checks follow proxy donor

[Andrea Righi <arighi@nvidia.com>]

Proxy execution separates the scheduling context in rq->donor from the
physical execution context in rq->curr. sched_can_stop_tick() checks the
latter for CFS bandwidth constraints and only does so when nr_running is
one.

A retained proxy donor keeps both the donor and mutex owner queued. The
check therefore misses a constrained FAIR donor and may stop the tick
while its runtime still needs to be enforced.

Check the selected donor instead and remove the nr_running restriction.
The donor being a queued FAIR task is sufficient to require bandwidth
accounting regardless of other runnable tasks.

Fixes: af0c8b2bf67b ("sched: Split scheduler and execution contexts")
Reported-by: Sashiko <sashiko-bot@kernel.org>
Link: https://lore.kernel.org/r/20260713164807.E5ED21F00A3A@smtp.kernel.org
Acked-by: John Stultz <jstultz@google.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/core.c | 35 ++++++++++++++++++-----------------
 kernel/sched/fair.c | 12 +++++++-----
 2 files changed, 25 insertions(+), 22 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 27164afc7b0aa..f47514ba6c241 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1420,11 +1420,8 @@ static void nohz_csd_func(void *info)
 #endif /* CONFIG_NO_HZ_COMMON */
 
 #ifdef CONFIG_NO_HZ_FULL
-static inline bool __need_bw_check(struct rq *rq, struct task_struct *p)
+static inline bool __need_bw_check(struct task_struct *p)
 {
-	if (rq->nr_running != 1)
-		return false;
-
 	if (p->sched_class != &fair_sched_class)
 		return false;
 
@@ -1442,6 +1439,14 @@ bool sched_can_stop_tick(struct rq *rq)
 	if (rq->dl.dl_nr_running)
 		return false;
 
+	/*
+	 * The selected scheduling context can be a constrained FAIR donor even
+	 * when rq->curr is an RT task. Check it before the RT fast paths below,
+	 * which may report that the tick can stop for a throttled RT context.
+	 */
+	if (__need_bw_check(rq->donor) && cfs_task_bw_constrained(rq->donor))
+		return false;
+
 	/*
 	 * If there are more than one RR tasks, we need the tick to affect the
 	 * actual RR behaviour.
@@ -1472,18 +1477,6 @@ bool sched_can_stop_tick(struct rq *rq)
 	if (rq->cfs.h_nr_queued > 1)
 		return false;
 
-	/*
-	 * If there is one task and it has CFS runtime bandwidth constraints
-	 * and it's on the cpu now we don't want to stop the tick.
-	 * This check prevents clearing the bit if a newly enqueued task here is
-	 * dequeued by migrating while the constrained task continues to run.
-	 * E.g. going from 2->1 without going through pick_next_task().
-	 */
-	if (__need_bw_check(rq, rq->curr)) {
-		if (cfs_task_bw_constrained(rq->curr))
-			return false;
-	}
-
 	return true;
 }
 #endif /* CONFIG_NO_HZ_FULL */
@@ -7105,7 +7098,7 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
  */
 static void __sched notrace __schedule(int sched_mode)
 {
-	struct task_struct *prev, *next;
+	struct task_struct *prev, *next, *tick_donor;
 	/*
 	 * On PREEMPT_RT kernel, SM_RTLOCK_WAIT is noted
 	 * as a preemption by schedule_debug() and RCU.
@@ -7159,6 +7152,7 @@ static void __sched notrace __schedule(int sched_mode)
 	rq->clock_update_flags <<= 1;
 	update_rq_clock(rq);
 	rq->clock_update_flags = RQCF_UPDATED;
+	tick_donor = rq->donor;
 
 	switch_count = &prev->nivcsw;
 
@@ -7234,6 +7228,13 @@ static void __sched notrace __schedule(int sched_mode)
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
 keep_resched:
+	/*
+	 * Enqueue and dequeue updates can evaluate the outgoing donor. Refresh
+	 * the dependency after selecting a different scheduling context.
+	 */
+	if (rq->donor != tick_donor)
+		sched_update_tick_dependency(rq);
+
 	rq->last_seen_need_resched_ns = 0;
 
 	is_switch = prev != next;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d78467ec6ee13..14c5b2aa01777 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7570,14 +7570,16 @@ static void sched_fair_update_stop_tick(struct rq *rq, struct task_struct *p)
 	if (!tick_nohz_full_cpu(cpu))
 		return;
 
-	if (rq->nr_running != 1)
+	if (rq->cfs.h_nr_queued != 1)
 		return;
 
 	/*
-	 *  We know there is only one task runnable and we've just picked it. The
-	 *  normal enqueue path will have cleared TICK_DEP_BIT_SCHED if we will
-	 *  be otherwise able to stop the tick. Just need to check if we are using
-	 *  bandwidth control.
+	 * We know there is only one FAIR task queued and we've just picked it.
+	 * The normal enqueue path will have cleared TICK_DEP_BIT_SCHED if we
+	 * will be otherwise able to stop the tick. With proxy execution, its
+	 * lock owner may remain runnable in another scheduling class, so
+	 * rq->nr_running can be greater than one. Just need to check if we are
+	 * using bandwidth control.
 	 */
 	if (cfs_task_bw_constrained(p))
 		tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
-- 
2.55.0