[RFC PATCH 15/22] sched/fair: Call resched_curr() from sched_notify_syscall_exit()

[K Prateek Nayak]

With pick_eevdf() marking a pick on throttled hierarchy with
"sched_throttled", reschedule the current when the "kernel_cs_count"
hits 0 if it was picked on a throttled hierarchy.

Signed-off-by: K Prateek Nayak <kprateek.nayak@xxxxxxx>
---
 kernel/sched/fair.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 68c194169c00..0332e95d36b5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6839,6 +6839,7 @@ bool cfs_task_bw_constrained(struct task_struct *p)
 
 __always_inline void sched_notify_critical_section_entry(void)
 {
+	SCHED_WARN_ON(current->se.kernel_cs_count);
 	current->se.kernel_cs_count++;
 	/*
 	 * Post this point, the task is considered to be in a kernel
@@ -6848,7 +6849,23 @@ __always_inline void sched_notify_critical_section_entry(void)
 
 __always_inline void sched_notify_critical_section_exit(void)
 {
+	lockdep_assert_irqs_disabled();
+
 	current->se.kernel_cs_count--;
+	SCHED_WARN_ON(current->se.kernel_cs_count);
+
+	/*
+	 * XXX: Can we get away with using set_thread_flag()
+	 * and not grabbing the rq_lock since we'll call
+	 * schedule() soon after enabling interrupts again in
+	 * exit_to_user_mode_loop()?
+	 */
+	if (!current->se.kernel_cs_count && current->se.sched_throttled) {
+		struct rq *rq = this_rq();
+
+		guard(rq_lock_irqsave)(rq);
+		resched_curr(rq);
+	}
 }
 
 static __always_inline int se_in_kernel(struct sched_entity *se)
-- 
2.43.0