[PATCH 3/5] sched_ext: Count kicks denied for lacking baseline cid access

[Tejun Heo <tj@kernel.org>]

kick_one_cpu() silently skips a kick when the kicking sub-sched lacks
SCX_CAP_BASE on the target cid, as does kick_one_cpu_if_idle() for idle
kicks. The skips are sound with the same logic as the reenq gate but are
invisible today, unlike the preempt degradation counted in
SCX_EV_SUB_PREEMPT_DENIED. Count them in a new SCX_EV_SUB_KICK_DENIED event
so every cap denial is observable.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext/ext.c      | 20 ++++++++++++++------
 kernel/sched/ext/internal.h |  8 ++++++++
 2 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index fd88b4d4f12a..5d02bb99c09d 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -8118,6 +8118,7 @@ static bool kick_one_cpu(s32 cpu, struct scx_sched_pcpu *pcpu, struct rq *this_r
 	struct scx_rq *this_scx = &this_rq->scx;
 	const struct sched_class *cur_class;
 	bool should_wait = false;
+	bool kickable;
 	unsigned long flags;
 
 	raw_spin_rq_lock_irqsave(rq, flags);
@@ -8131,9 +8132,10 @@ static bool kick_one_cpu(s32 cpu, struct scx_sched_pcpu *pcpu, struct rq *this_r
 	 * business forcing a reschedule there - skip. This is the authoritative
 	 * cap check: ecaps is read here under @rq's lock.
 	 */
-	if ((cpu_online(cpu) || cpu == cpu_of(this_rq)) &&
-	    !sched_class_above(cur_class, &ext_sched_class) &&
-	    !scx_missing_caps(pcpu->sch, cpu, SCX_CAP_BASE)) {
+	kickable = (cpu_online(cpu) || cpu == cpu_of(this_rq)) &&
+		   !sched_class_above(cur_class, &ext_sched_class);
+
+	if (kickable && !scx_missing_caps(pcpu->sch, cpu, SCX_CAP_BASE)) {
 		if (cpumask_test_cpu(cpu, pcpu->cpus_to_preempt)) {
 			if (cur_class == &ext_sched_class) {
 				if (likely(!scx_missing_caps(pcpu->sch, cpu,
@@ -8157,6 +8159,9 @@ static bool kick_one_cpu(s32 cpu, struct scx_sched_pcpu *pcpu, struct rq *this_r
 
 		resched_curr(rq);
 	} else {
+		/* a kickable cpu was skipped solely for the missing caps */
+		if (kickable)
+			__scx_add_event(pcpu->sch, SCX_EV_SUB_KICK_DENIED, 1);
 		cpumask_clear_cpu(cpu, pcpu->cpus_to_preempt);
 		cpumask_clear_cpu(cpu, pcpu->cpus_to_wait);
 	}
@@ -8176,9 +8181,12 @@ static void kick_one_cpu_if_idle(s32 cpu, struct scx_sched_pcpu *pcpu,
 
 	/* idle kicks need baseline access too, see kick_one_cpu() */
 	if (!can_skip_idle_kick(rq) &&
-	    (cpu_online(cpu) || cpu == cpu_of(this_rq)) &&
-	    !scx_missing_caps(pcpu->sch, cpu, SCX_CAP_BASE))
-		resched_curr(rq);
+	    (cpu_online(cpu) || cpu == cpu_of(this_rq))) {
+		if (likely(!scx_missing_caps(pcpu->sch, cpu, SCX_CAP_BASE)))
+			resched_curr(rq);
+		else
+			__scx_add_event(pcpu->sch, SCX_EV_SUB_KICK_DENIED, 1);
+	}
 
 	raw_spin_rq_unlock_irqrestore(rq, flags);
 }
diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h
index 1bdf34f3fc3c..308d16320818 100644
--- a/kernel/sched/ext/internal.h
+++ b/kernel/sched/ext/internal.h
@@ -1194,6 +1194,13 @@ struct scx_event_stats {
 	 */
 	s64		SCX_EV_SUB_PREEMPT_DENIED;
 
+	/*
+	 * The number of times a kick was skipped because the sub-sched lacked
+	 * baseline access on the target cid. The preempt-part degradation of a
+	 * delivered kick is counted in SCX_EV_SUB_PREEMPT_DENIED instead.
+	 */
+	s64		SCX_EV_SUB_KICK_DENIED;
+
 	/*
 	 * The number of times a local DSQ reenq was dropped because the
 	 * sub-sched lacked baseline access on the target cid.
@@ -1219,6 +1226,7 @@ struct scx_event_stats {
 	SCX_EVENT(SCX_EV_SUB_BYPASS_DISPATCH);				\
 	SCX_EVENT(SCX_EV_SUB_FORCED_ADMIT);				\
 	SCX_EVENT(SCX_EV_SUB_PREEMPT_DENIED);				\
+	SCX_EVENT(SCX_EV_SUB_KICK_DENIED);				\
 	SCX_EVENT(SCX_EV_SUB_REENQ_DENIED)
 
 struct scx_sched;
-- 
2.55.0