[PATCH 01/10] sched: Add vCPU debooster infrastructure

[Wanpeng Li]

From: Wanpeng Li <wanpengli@xxxxxxxxxxx>

From: Wanpeng Li <wanpengli@xxxxxxxxxxx>

Introduce foundational infrastructure for the vCPU debooster mechanism
to improve yield_to() effectiveness in virtualization workloads.

Add per-rq tracking fields for rate limiting (yield_deboost_last_time_ns)
and debouncing (yield_deboost_last_src/dst_pid, last_pair_time_ns).
Introduce global sysctl knob sysctl_sched_vcpu_debooster_enabled for
runtime control, defaulting to enabled. Add debugfs interface for
observability and initialization in sched_init().

The infrastructure is inert at this stage as no deboost logic is
implemented yet, allowing independent verification that existing
behavior remains unchanged.

Signed-off-by: Wanpeng Li <wanpengli@xxxxxxxxxxx>
---
 kernel/sched/core.c  | 7 +++++--
 kernel/sched/debug.c | 3 +++
 kernel/sched/fair.c  | 5 +++++
 kernel/sched/sched.h | 9 +++++++++
 4 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f754a60de848..03380790088b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8706,9 +8706,12 @@ void __init sched_init(void)
 #endif /* CONFIG_CGROUP_SCHED */
 
 	for_each_possible_cpu(i) {
-		struct rq *rq;
+		struct rq *rq = cpu_rq(i);
+		/* init per-rq debounce tracking */
+		rq->yield_deboost_last_src_pid = -1;
+		rq->yield_deboost_last_dst_pid = -1;
+		rq->yield_deboost_last_pair_time_ns = 0;
 
-		rq = cpu_rq(i);
 		raw_spin_lock_init(&rq->__lock);
 		rq->nr_running = 0;
 		rq->calc_load_active = 0;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 02e16b70a790..905f303af752 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -508,6 +508,9 @@ static __init int sched_init_debug(void)
 	debugfs_create_file("tunable_scaling", 0644, debugfs_sched, NULL, &sched_scaling_fops);
 	debugfs_create_u32("migration_cost_ns", 0644, debugfs_sched, &sysctl_sched_migration_cost);
 	debugfs_create_u32("nr_migrate", 0644, debugfs_sched, &sysctl_sched_nr_migrate);
+	debugfs_create_u32("sched_vcpu_debooster_enabled", 0644, debugfs_sched,
+		&sysctl_sched_vcpu_debooster_enabled);
+
 
 	sched_domains_mutex_lock();
 	update_sched_domain_debugfs();
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5b752324270b..5b7fcc86ccff 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -81,6 +81,11 @@ static unsigned int normalized_sysctl_sched_base_slice	= 700000ULL;
 
 __read_mostly unsigned int sysctl_sched_migration_cost	= 500000UL;
 
+/*
+ * vCPU debooster sysctl control
+ */
+unsigned int sysctl_sched_vcpu_debooster_enabled __read_mostly = 1;
+
 static int __init setup_sched_thermal_decay_shift(char *str)
 {
 	pr_warn("Ignoring the deprecated sched_thermal_decay_shift= option\n");
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index adfb6e3409d7..e9b4be024f89 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1292,6 +1292,13 @@ struct rq {
 	unsigned int		push_busy;
 	struct cpu_stop_work	push_work;
 
+	/* vCPU debooster rate-limit */
+	u64			yield_deboost_last_time_ns;
+	/* per-rq debounce state to avoid cross-CPU races */
+	pid_t			yield_deboost_last_src_pid;
+	pid_t			yield_deboost_last_dst_pid;
+	u64			yield_deboost_last_pair_time_ns;
+
 #ifdef CONFIG_SCHED_CORE
 	/* per rq */
 	struct rq		*core;
@@ -2816,6 +2823,8 @@ extern int sysctl_resched_latency_warn_once;
 
 extern unsigned int sysctl_sched_tunable_scaling;
 
+extern unsigned int sysctl_sched_vcpu_debooster_enabled;
+
 extern unsigned int sysctl_numa_balancing_scan_delay;
 extern unsigned int sysctl_numa_balancing_scan_period_min;
 extern unsigned int sysctl_numa_balancing_scan_period_max;
-- 
2.43.0