Re: [RFC 06/10] Reclaim memory from blocked kernel stacks

[Peter Zijlstra <peterz@infradead.org>]

On Fri, Aug 28, 2026 at 03:17:47PM -0400, Steven Rostedt wrote:

>   1)     8072     104   update_group_capacity+0x94/0x960
>   2)     7968     528   update_sd_lb_stats.constprop.0+0x426/0x39b0
>   3)     7440     424   sched_balance_find_src_group+0x8f/0x1150
>   4)     7016     552   sched_balance_rq+0x934/0x4130

Bah, yeah, those on-stack statistics just keep growing.

This should probably help. Very lightly tested. Also we can probably
relax the assertion to bh-disabled and avoid the extra irq-disable
around sched_balance_rq().

Anybody got time to play around with this?

---
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8dff37059faf..0c83b0856a95 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -11418,6 +11418,39 @@ struct sd_lb_stats {
 	struct sg_lb_stats local_stat;		/* Statistics of the local group */
 };
 
+struct pcpu_lb_stats {
+	struct sd_lb_stats sds;
+	struct sg_lb_stats sgs;
+	struct sg_lb_stats local_sgs;
+	struct sg_lb_stats idlest_sgs;
+};
+
+static DEFINE_PER_CPU(struct pcpu_lb_stats, pcpu_lb_stats);
+
+static inline struct sd_lb_stats *this_sds(void)
+{
+	lockdep_assert_irqs_disabled();
+	return this_cpu_ptr(&pcpu_lb_stats.sds);
+}
+
+static inline struct sg_lb_stats *this_sgs(void)
+{
+	lockdep_assert_irqs_disabled();
+	return this_cpu_ptr(&pcpu_lb_stats.sgs);
+}
+
+static inline struct sg_lb_stats *this_local_sgs(void)
+{
+	lockdep_assert_irqs_disabled();
+	return this_cpu_ptr(&pcpu_lb_stats.local_sgs);
+}
+
+static inline struct sg_lb_stats *this_idlest_sgs(void)
+{
+	lockdep_assert_irqs_disabled();
+	return this_cpu_ptr(&pcpu_lb_stats.idlest_sgs);
+}
+
 static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
 {
 	/*
@@ -12406,12 +12439,13 @@ static struct sched_group *
 sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 {
 	struct sched_group *idlest = NULL, *local = NULL, *group = sd->groups;
-	struct sg_lb_stats local_sgs, tmp_sgs;
+	struct sg_lb_stats *local_sgs = this_local_sgs();
 	struct sg_lb_stats *sgs;
 	unsigned long imbalance;
-	struct sg_lb_stats idlest_sgs = {
-			.avg_load = UINT_MAX,
-			.group_type = group_overloaded,
+	struct sg_lb_stats *idlest_sgs = this_idlest_sgs();
+	*idlest_sgs = (struct sg_lb_stats){
+		.avg_load = UINT_MAX,
+		.group_type = group_overloaded,
 	};
 
 	do {
@@ -12430,17 +12464,17 @@ sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int
 					       sched_group_span(group));
 
 		if (local_group) {
-			sgs = &local_sgs;
+			sgs = local_sgs;
 			local = group;
 		} else {
-			sgs = &tmp_sgs;
+			sgs = this_sgs();
 		}
 
 		update_sg_wakeup_stats(sd, group, sgs, p);
 
-		if (!local_group && update_pick_idlest(idlest, &idlest_sgs, group, sgs)) {
+		if (!local_group && update_pick_idlest(idlest, idlest_sgs, group, sgs)) {
 			idlest = group;
-			idlest_sgs = *sgs;
+			*idlest_sgs = *sgs;
 		}
 
 	} while (group = group->next, group != sd->groups);
@@ -12458,17 +12492,17 @@ sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int
 	 * If the local group is idler than the selected idlest group
 	 * don't try and push the task.
 	 */
-	if (local_sgs.group_type < idlest_sgs.group_type)
+	if (local_sgs->group_type < idlest_sgs->group_type)
 		return NULL;
 
 	/*
 	 * If the local group is busier than the selected idlest group
 	 * try and push the task.
 	 */
-	if (local_sgs.group_type > idlest_sgs.group_type)
+	if (local_sgs->group_type > idlest_sgs->group_type)
 		return idlest;
 
-	switch (local_sgs.group_type) {
+	switch (local_sgs->group_type) {
 	case group_overloaded:
 	case group_fully_busy:
 
@@ -12486,17 +12520,17 @@ sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int
 		 */
 
 		if ((sd->flags & SD_NUMA) &&
-		    ((idlest_sgs.avg_load + imbalance) >= local_sgs.avg_load))
+		    ((idlest_sgs->avg_load + imbalance) >= local_sgs->avg_load))
 			return NULL;
 
 		/*
 		 * If the local group is less loaded than the selected
 		 * idlest group don't try and push any tasks.
 		 */
-		if (idlest_sgs.avg_load >= (local_sgs.avg_load + imbalance))
+		if (idlest_sgs->avg_load >= (local_sgs->avg_load + imbalance))
 			return NULL;
 
-		if (100 * local_sgs.avg_load <= sd->imbalance_pct * idlest_sgs.avg_load)
+		if (100 * local_sgs->avg_load <= sd->imbalance_pct * idlest_sgs->avg_load)
 			return NULL;
 		break;
 
@@ -12545,9 +12579,9 @@ sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int
 				imb_numa_nr = min(w, sd->imb_numa_nr);
 			}
 
-			imbalance = abs(local_sgs.idle_cpus - idlest_sgs.idle_cpus);
+			imbalance = abs(local_sgs->idle_cpus - idlest_sgs->idle_cpus);
 			if (!adjust_numa_imbalance(imbalance,
-						   local_sgs.sum_nr_running + 1,
+						   local_sgs->sum_nr_running + 1,
 						   imb_numa_nr)) {
 				return NULL;
 			}
@@ -12560,7 +12594,7 @@ sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int
 		 * up that the group has less spare capacity but finally more
 		 * idle CPUs which means more opportunity to run task.
 		 */
-		if (local_sgs.idle_cpus >= idlest_sgs.idle_cpus)
+		if (local_sgs->idle_cpus >= idlest_sgs->idle_cpus)
 			return NULL;
 		break;
 	}
@@ -12647,14 +12681,13 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 {
 	struct sched_group *sg = env->sd->groups;
 	struct sg_lb_stats *local = &sds->local_stat;
-	struct sg_lb_stats tmp_sgs;
 	unsigned long sum_util = 0;
 	bool sg_overloaded = 0, sg_overutilized = 0;
 
 	env->dst_core_idle = !sched_smt_active() || is_core_idle(env->dst_cpu);
 
 	do {
-		struct sg_lb_stats *sgs = &tmp_sgs;
+		struct sg_lb_stats *sgs = this_sgs();
 		int local_group;
 
 		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(sg));
@@ -12929,21 +12962,21 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 static struct sched_group *sched_balance_find_src_group(struct lb_env *env)
 {
 	struct sg_lb_stats *local, *busiest;
-	struct sd_lb_stats sds;
+	struct sd_lb_stats *sds = this_sds();
 
-	init_sd_lb_stats(&sds);
+	init_sd_lb_stats(sds);
 
 	/*
 	 * Compute the various statistics relevant for load balancing at
 	 * this level.
 	 */
-	update_sd_lb_stats(env, &sds);
+	update_sd_lb_stats(env, sds);
 
 	/* There is no busy sibling group to pull tasks from */
-	if (!sds.busiest)
+	if (!sds->busiest)
 		goto out_balanced;
 
-	busiest = &sds.busiest_stat;
+	busiest = &sds->busiest_stat;
 
 	/* Misfit tasks should be dealt with regardless of the avg load */
 	if (busiest->group_type == group_misfit_task)
@@ -12965,7 +12998,7 @@ static struct sched_group *sched_balance_find_src_group(struct lb_env *env)
 	if (busiest->group_type == group_imbalanced)
 		goto force_balance;
 
-	local = &sds.local_stat;
+	local = &sds->local_stat;
 	/*
 	 * If the local group is busier than the selected busiest group
 	 * don't try and pull any tasks.
@@ -12986,14 +13019,14 @@ static struct sched_group *sched_balance_find_src_group(struct lb_env *env)
 			goto out_balanced;
 
 		/* XXX broken for overlapping NUMA groups */
-		sds.avg_load = (sds.total_load * SCHED_CAPACITY_SCALE) /
-				sds.total_capacity;
+		sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) /
+				sds->total_capacity;
 
 		/*
 		 * Don't pull any tasks if this group is already above the
 		 * domain average load.
 		 */
-		if (local->avg_load >= sds.avg_load)
+		if (local->avg_load >= sds->avg_load)
 			goto out_balanced;
 
 		/*
@@ -13009,9 +13042,9 @@ static struct sched_group *sched_balance_find_src_group(struct lb_env *env)
 	 * Try to move all excess tasks to a sibling domain of the busiest
 	 * group's child domain.
 	 */
-	if (sds.prefer_sibling && local->group_type == group_has_spare &&
+	if (sds->prefer_sibling && local->group_type == group_has_spare &&
 	    (busiest->group_type == group_llc_balance ||
-	    sibling_imbalance(env, &sds, busiest, local) > 1))
+	    sibling_imbalance(env, sds, busiest, local) > 1))
 		goto force_balance;
 
 	if (busiest->group_type != group_overloaded) {
@@ -13025,7 +13058,7 @@ static struct sched_group *sched_balance_find_src_group(struct lb_env *env)
 		}
 
 		if (busiest->group_type == group_smt_balance &&
-		    smt_vs_nonsmt_groups(sds.local, sds.busiest)) {
+		    smt_vs_nonsmt_groups(sds->local, sds->busiest)) {
 			/* Let non SMT CPU pull from SMT CPU sharing with sibling */
 			goto force_balance;
 		}
@@ -13054,8 +13087,8 @@ static struct sched_group *sched_balance_find_src_group(struct lb_env *env)
 
 force_balance:
 	/* Looks like there is an imbalance. Compute it */
-	calculate_imbalance(env, &sds);
-	return env->imbalance ? sds.busiest : NULL;
+	calculate_imbalance(env, sds);
+	return env->imbalance ? sds->busiest : NULL;
 
 out_balanced:
 	env->imbalance = 0;
@@ -13958,6 +13991,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
 
 		interval = get_sd_balance_interval(sd, busy);
 		if (time_after_eq(jiffies, sd->last_balance + interval)) {
+			guard(irqsave)();
 			if (sched_balance_rq(cpu, rq, sd, idle, &continue_balancing)) {
 				/*
 				 * The LBF_DST_PINNED logic could have changed