sched/core: Fix wakeup_preempt's next_class tracking

Kernel test robot reported that
tools/testing/selftests/kvm/hardware_disable_test was failing due to
commit 704069649b5b ("sched/core: Rework sched_class::wakeup_preempt()
and rq_modified_*()")

It turns out there were two related problems that could lead to a
missed preemption:

 - when hitting newidle balance from the idle thread, it would elevate
   rb->next_class from &idle_sched_class to &fair_sched_class, causing
   later wakeup_preempt() calls to not hit the sched_class_above()
   case, and not issue resched_curr().

   Notably, this modification pattern should only lower the
   next_class, and never raise it. Create two new helper functions to
   wrap this.

 - when doing schedule_idle(), it was possible to miss (re)setting
   rq->next_class to &idle_sched_class, leading to the very same
   problem.

Cc: Sean Christopherson <seanjc@google.com>
Fixes: 704069649b5b ("sched/core: Rework sched_class::wakeup_preempt() and rq_modified_*()")
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202602122157.4e861298-lkp@intel.com
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260218163329.GQ1395416@noisy.programming.kicks-ass.net

4 files changed, 16 insertions, 4 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 759777694c78..b7f77c165a6e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6830,6 +6830,7 @@ static void __sched notrace __schedule(int sched_mode)
 		/* SCX must consult the BPF scheduler to tell if rq is empty */
 		if (!rq->nr_running && !scx_enabled()) {
 			next = prev;
+			rq->next_class = &idle_sched_class;
 			goto picked;
 		}
 	} else if (!preempt && prev_state) {
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 62b1f3ac5630..06cc0a4aec66 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2460,7 +2460,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx)
 	/* see kick_cpus_irq_workfn() */
 	smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1);
 
-	rq->next_class = &ext_sched_class;
+	rq_modified_begin(rq, &ext_sched_class);
 
 	rq_unpin_lock(rq, rf);
 	balance_one(rq, prev);
@@ -2475,7 +2475,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx)
 	 * If @force_scx is true, always try to pick a SCHED_EXT task,
 	 * regardless of any higher-priority sched classes activity.
 	 */
-	if (!force_scx && sched_class_above(rq->next_class, &ext_sched_class))
+	if (!force_scx && rq_modified_above(rq, &ext_sched_class))
 		return RETRY_TASK;
 
 	keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f4446cbe8ffa..bf948db905ed 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12982,7 +12982,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 	t0 = sched_clock_cpu(this_cpu);
 	__sched_balance_update_blocked_averages(this_rq);
 
-	this_rq->next_class = &fair_sched_class;
+	rq_modified_begin(this_rq, &fair_sched_class);
 	raw_spin_rq_unlock(this_rq);
 
 	for_each_domain(this_cpu, sd) {
@@ -13049,7 +13049,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 		pulled_task = 1;
 
 	/* If a higher prio class was modified, restart the pick */
-	if (sched_class_above(this_rq->next_class, &fair_sched_class))
+	if (rq_modified_above(this_rq, &fair_sched_class))
 		pulled_task = -1;
 
 out:
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b82fb70a9d54..43bbf0693cca 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2748,6 +2748,17 @@ static inline const struct sched_class *next_active_class(const struct sched_cla
 
 #define sched_class_above(_a, _b)	((_a) < (_b))
 
+static inline void rq_modified_begin(struct rq *rq, const struct sched_class *class)
+{
+	if (sched_class_above(rq->next_class, class))
+		rq->next_class = class;
+}
+
+static inline bool rq_modified_above(struct rq *rq, const struct sched_class *class)
+{
+	return sched_class_above(rq->next_class, class);
+}
+
 static inline bool sched_stop_runnable(struct rq *rq)
 {
 	return rq->stop && task_on_rq_queued(rq->stop);