sched/fair: Remove task_group->se pointer array

Now that struct sched_entity is co-located with struct cfs_rq for non-root task
groups, the task_group->se pointer array is redundant. The associated
sched_entity can be loaded directly from the cfs_rq.

This patch performs the access conversion with the helpers:

 - is_root_task_group(tg): checks if a task group is the root task group. It
   compares the task group's address with the global root_task_group variable.

 - tg_se(tg, cpu): retrieves the cfs_rq and returns the address of the
   co-located se. This function checks if tg is the root task group to ensure
   behaving the same of previous tg->se[cpu]. Replaces all accesses that use
   the tg->se[cpu] pointer array with calls to the new tg_se(tg, cpu) accessor.

 - cfs_rq_se(cfs_rq): simplifies access paths like cfs_rq->tg->se[...] to use
   the co-located sched_entity. This function also checks if tg is the root
   task group to ensure same behavior.

Since tg_se is not in very hot code paths, and the branch is a register
comparison with an immediate value (`&root_task_group`), the performance impact
is expected to be negligible.

Signed-off-by: Zecheng Li <zecheng@google.com>
Signed-off-by: Zecheng Li <zli94@ncsu.edu>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: K Prateek Nayak <kprateek.nayak@amd.com>
Reviewed-by: Josh Don <joshdon@google.com>
Link: https://patch.msgid.link/20260522141623.600235-3-zli94@ncsu.edu

kernel/sched/core.c

@@ -8923,7 +8923,7 @@ void __init sched_init(void)
 	wait_bit_init();
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	ptr += 2 * nr_cpu_ids * sizeof(void **);
+	ptr += nr_cpu_ids * sizeof(void **);
 #endif
 #ifdef CONFIG_RT_GROUP_SCHED
 	ptr += 2 * nr_cpu_ids * sizeof(void **);
@@ -8932,9 +8932,6 @@ void __init sched_init(void)
 		ptr = (unsigned long)kzalloc(ptr, GFP_NOWAIT);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-		root_task_group.se = (struct sched_entity **)ptr;
-		ptr += nr_cpu_ids * sizeof(void **);
-
 		root_task_group.cfs_rq = (struct cfs_rq **)ptr;
 		ptr += nr_cpu_ids * sizeof(void **);
 
@@ -10016,7 +10013,7 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
 		int i;
 
 		for_each_possible_cpu(i) {
-			stats = __schedstats_from_se(tg->se[i]);
+			stats = __schedstats_from_se(tg_se(tg, i));
 			ws += schedstat_val(stats->wait_sum);
 		}
 

kernel/sched/debug.c

@@ -808,7 +808,7 @@ void dirty_sched_domain_sysctl(int cpu)
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
 {
-	struct sched_entity *se = tg->se[cpu];
+	struct sched_entity *se = tg_se(tg, cpu);
 
 #define P(F)		SEQ_printf(m, "  .%-30s: %lld\n",	#F, (long long)F)
 #define P_SCHEDSTAT(F)	SEQ_printf(m, "  .%-30s: %lld\n",	\

kernel/sched/fair.c

@@ -6876,7 +6876,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
-	struct sched_entity *se = cfs_rq->tg->se[cpu_of(rq)];
+	struct sched_entity *se = cfs_rq_se(cfs_rq);
 
 	/*
 	 * It's possible we are called with runtime_remaining < 0 due to things
@@ -11102,7 +11102,6 @@ static bool __update_blocked_fair(struct rq *rq, bool *done)
 {
 	struct cfs_rq *cfs_rq, *pos;
 	bool decayed = false;
-	int cpu = cpu_of(rq);
 
 	/*
 	 * Iterates the task_group tree in a bottom up fashion, see
@@ -11122,7 +11121,7 @@ static bool __update_blocked_fair(struct rq *rq, bool *done)
 		}
 
 		/* Propagate pending load changes to the parent, if any: */
-		se = cfs_rq->tg->se[cpu];
+		se = cfs_rq_se(cfs_rq);
 		if (se && !skip_blocked_update(se))
 			update_load_avg(cfs_rq_of(se), se, UPDATE_TG);
 
@@ -11148,8 +11147,7 @@ static bool __update_blocked_fair(struct rq *rq, bool *done)
  */
 static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 {
-	struct rq *rq = rq_of(cfs_rq);
-	struct sched_entity *se = cfs_rq->tg->se[cpu_of(rq)];
+	struct sched_entity *se = cfs_rq_se(cfs_rq);
 	unsigned long now = jiffies;
 	unsigned long load;
 
@@ -15086,7 +15084,6 @@ void free_fair_sched_group(struct task_group *tg)
 	}
 
 	kfree(tg->cfs_rq);
-	kfree(tg->se);
 }
 
 int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
@@ -15099,9 +15096,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	tg->cfs_rq = kzalloc_objs(cfs_rq, nr_cpu_ids);
 	if (!tg->cfs_rq)
 		goto err;
-	tg->se = kzalloc_objs(se, nr_cpu_ids);
-	if (!tg->se)
-		goto err;
 
 	tg->shares = NICE_0_LOAD;
 
@@ -15116,7 +15110,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 		cfs_rq = &state->cfs_rq;
 		se = &state->se;
 		init_cfs_rq(cfs_rq);
-		init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
+		init_tg_cfs_entry(tg, cfs_rq, se, i, tg_se(parent, i));
 		init_entity_runnable_average(se);
 	}
 
@@ -15135,7 +15129,7 @@ void online_fair_sched_group(struct task_group *tg)
 
 	for_each_possible_cpu(i) {
 		rq = cpu_rq(i);
-		se = tg->se[i];
+		se = tg_se(tg, i);
 		rq_lock_irq(rq, &rf);
 		update_rq_clock(rq);
 		attach_entity_cfs_rq(se);
@@ -15152,7 +15146,7 @@ void unregister_fair_sched_group(struct task_group *tg)
 
 	for_each_possible_cpu(cpu) {
 		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu];
-		struct sched_entity *se = tg->se[cpu];
+		struct sched_entity *se = tg_se(tg, cpu);
 		struct rq *rq = cpu_rq(cpu);
 
 		if (se) {
@@ -15189,7 +15183,6 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 	init_cfs_rq_runtime(cfs_rq);
 
 	tg->cfs_rq[cpu] = cfs_rq;
-	tg->se[cpu] = se;
 
 	/* se could be NULL for root_task_group */
 	if (!se)
@@ -15220,7 +15213,7 @@ static int __sched_group_set_shares(struct task_group *tg, unsigned long shares)
 	/*
 	 * We can't change the weight of the root cgroup.
 	 */
-	if (!tg->se[0])
+	if (is_root_task_group(tg))
 		return -EINVAL;
 
 	shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES));
@@ -15231,7 +15224,7 @@ static int __sched_group_set_shares(struct task_group *tg, unsigned long shares)
 	tg->shares = shares;
 	for_each_possible_cpu(i) {
 		struct rq *rq = cpu_rq(i);
-		struct sched_entity *se = tg->se[i];
+		struct sched_entity *se = tg_se(tg, i);
 		struct rq_flags rf;
 
 		/* Propagate contribution to hierarchy */
@@ -15282,7 +15275,7 @@ int sched_group_set_idle(struct task_group *tg, long idle)
 
 	for_each_possible_cpu(i) {
 		struct rq *rq = cpu_rq(i);
-		struct sched_entity *se = tg->se[i];
+		struct sched_entity *se = tg_se(tg, i);
 		struct cfs_rq *grp_cfs_rq = tg->cfs_rq[i];
 		bool was_idle = cfs_rq_is_idle(grp_cfs_rq);
 		long idle_task_delta;

kernel/sched/sched.h

@@ -484,8 +484,6 @@ struct task_group {
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	/* schedulable entities of this group on each CPU */
-	struct sched_entity	**se;
 	/* runqueue "owned" by this group on each CPU */
 	struct cfs_rq		**cfs_rq;
 	unsigned long		shares;
@@ -934,7 +932,8 @@ struct dl_rq {
 };
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-
+/* Check whether a task group is root tg */
+#define is_root_task_group(tg) ((tg) == &root_task_group)
 /* An entity is a task if it doesn't "own" a runqueue */
 #define entity_is_task(se)	(!se->my_q)
 
@@ -2304,6 +2303,28 @@ struct cfs_tg_state {
 	struct sched_entity	se;
 	struct sched_statistics	stats;
 } __no_randomize_layout;
+
+static inline struct sched_entity *tg_se(struct task_group *tg, int cpu)
+{
+	struct cfs_tg_state *state;
+
+	if (is_root_task_group(tg))
+		return NULL;
+
+	state = container_of(tg->cfs_rq[cpu], struct cfs_tg_state, cfs_rq);
+	return &state->se;
+}
+
+static inline struct sched_entity *cfs_rq_se(struct cfs_rq *cfs_rq)
+{
+	struct cfs_tg_state *state;
+
+	if (is_root_task_group(cfs_rq->tg))
+		return NULL;
+
+	state = container_of(cfs_rq, struct cfs_tg_state, cfs_rq);
+	return &state->se;
+}
 #endif
 
 /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
@@ -2316,8 +2337,8 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	set_task_rq_fair(&p->se, p->se.cfs_rq, tg->cfs_rq[cpu]);
 	p->se.cfs_rq = tg->cfs_rq[cpu];
-	p->se.parent = tg->se[cpu];
-	p->se.depth = tg->se[cpu] ? tg->se[cpu]->depth + 1 : 0;
+	p->se.parent = tg_se(tg, cpu);
+	p->se.depth = p->se.parent ? p->se.parent->depth + 1 : 0;
 #endif
 
 #ifdef CONFIG_RT_GROUP_SCHED