sched/fair: Proportional newidle balance

Add a randomized algorithm that runs newidle balancing proportional to
its success rate.

This improves schbench significantly:

 6.18-rc4:			2.22 Mrps/s
 6.18-rc4+revert:		2.04 Mrps/s
 6.18-rc4+revert+random:	2.18 Mrps/S

Conversely, per Adam Li this affects SpecJBB slightly, reducing it by 1%:

 6.17:			-6%
 6.17+revert:		 0%
 6.17+revert+random:	-1%

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Chris Mason <clm@meta.com>
Link: https://lkml.kernel.org/r/6825c50d-7fa7-45d8-9b81-c6e7e25738e2@meta.com
Link: https://patch.msgid.link/20251107161739.770122091@infradead.org

include/linux/sched/topology.h

@@ -92,6 +92,9 @@ struct sched_domain {
 	unsigned int nr_balance_failed; /* initialise to 0 */
 
 	/* idle_balance() stats */
+	unsigned int newidle_call;
+	unsigned int newidle_success;
+	unsigned int newidle_ratio;
 	u64 max_newidle_lb_cost;
 	unsigned long last_decay_max_lb_cost;
 

kernel/sched/core.c

@@ -121,6 +121,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+DEFINE_PER_CPU(struct rnd_state, sched_rnd_state);
 
 #ifdef CONFIG_SCHED_PROXY_EXEC
 DEFINE_STATIC_KEY_TRUE(__sched_proxy_exec);
@@ -8489,6 +8490,8 @@ void __init sched_init_smp(void)
 {
 	sched_init_numa(NUMA_NO_NODE);
 
+	prandom_init_once(&sched_rnd_state);
+
 	/*
 	 * There's no userspace yet to cause hotplug operations; hence all the
 	 * CPU masks are stable and all blatant races in the below code cannot

kernel/sched/fair.c

@@ -12224,11 +12224,27 @@ void update_max_interval(void)
 	max_load_balance_interval = HZ*num_online_cpus()/10;
 }
 
-static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost)
+static inline void update_newidle_stats(struct sched_domain *sd, unsigned int success)
+{
+	sd->newidle_call++;
+	sd->newidle_success += success;
+
+	if (sd->newidle_call >= 1024) {
+		sd->newidle_ratio = sd->newidle_success;
+		sd->newidle_call /= 2;
+		sd->newidle_success /= 2;
+	}
+}
+
+static inline bool
+update_newidle_cost(struct sched_domain *sd, u64 cost, unsigned int success)
 {
 	unsigned long next_decay = sd->last_decay_max_lb_cost + HZ;
 	unsigned long now = jiffies;
 
+	if (cost)
+		update_newidle_stats(sd, success);
+
 	if (cost > sd->max_newidle_lb_cost) {
 		/*
 		 * Track max cost of a domain to make sure to not delay the
@@ -12276,7 +12292,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
 		 * Decay the newidle max times here because this is a regular
 		 * visit to all the domains.
 		 */
-		need_decay = update_newidle_cost(sd, 0);
+		need_decay = update_newidle_cost(sd, 0, 0);
 		max_cost += sd->max_newidle_lb_cost;
 
 		/*
@@ -12912,6 +12928,22 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 			break;
 
 		if (sd->flags & SD_BALANCE_NEWIDLE) {
+			unsigned int weight = 1;
+
+			if (sched_feat(NI_RANDOM)) {
+				/*
+				 * Throw a 1k sided dice; and only run
+				 * newidle_balance according to the success
+				 * rate.
+				 */
+				u32 d1k = sched_rng() % 1024;
+				weight = 1 + sd->newidle_ratio;
+				if (d1k > weight) {
+					update_newidle_stats(sd, 0);
+					continue;
+				}
+				weight = (1024 + weight/2) / weight;
+			}
 
 			pulled_task = sched_balance_rq(this_cpu, this_rq,
 						   sd, CPU_NEWLY_IDLE,
@@ -12919,10 +12951,14 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 
 			t1 = sched_clock_cpu(this_cpu);
 			domain_cost = t1 - t0;
-			update_newidle_cost(sd, domain_cost);
-
 			curr_cost += domain_cost;
 			t0 = t1;
+
+			/*
+			 * Track max cost of a domain to make sure to not delay the
+			 * next wakeup on the CPU.
+			 */
+			update_newidle_cost(sd, domain_cost, weight * !!pulled_task);
 		}
 
 		/*

kernel/sched/features.h

@@ -121,3 +121,8 @@ SCHED_FEAT(WA_BIAS, true)
 SCHED_FEAT(UTIL_EST, true)
 
 SCHED_FEAT(LATENCY_WARN, false)
+
+/*
+ * Do newidle balancing proportional to its success rate using randomization.
+ */
+SCHED_FEAT(NI_RANDOM, true)

kernel/sched/sched.h

@@ -5,6 +5,7 @@
 #ifndef _KERNEL_SCHED_SCHED_H
 #define _KERNEL_SCHED_SCHED_H
 
+#include <linux/prandom.h>
 #include <linux/sched/affinity.h>
 #include <linux/sched/autogroup.h>
 #include <linux/sched/cpufreq.h>
@@ -1348,6 +1349,12 @@ static inline bool is_migration_disabled(struct task_struct *p)
 }
 
 DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+DECLARE_PER_CPU(struct rnd_state, sched_rnd_state);
+
+static inline u32 sched_rng(void)
+{
+	return prandom_u32_state(this_cpu_ptr(&sched_rnd_state));
+}
 
 #define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
 #define this_rq()		this_cpu_ptr(&runqueues)

kernel/sched/topology.c

@@ -1669,6 +1669,12 @@ sd_init(struct sched_domain_topology_level *tl,
 
 		.last_balance		= jiffies,
 		.balance_interval	= sd_weight,
+
+		/* 50% success rate */
+		.newidle_call		= 512,
+		.newidle_success	= 256,
+		.newidle_ratio		= 512,
+
 		.max_newidle_lb_cost	= 0,
 		.last_decay_max_lb_cost	= jiffies,
 		.child			= child,