sched/fair: Allocate cfs_tg_state with percpu allocator

To remove the cfs_rq pointer array in task_group, allocate the combined
cfs_rq and sched_entity using the per-cpu allocator.

This patch implements the following:

 - Changes task_group->cfs_rq from 'struct cfs_rq **' to
   'struct cfs_rq __percpu *'.

 - Updates memory allocation in alloc_fair_sched_group() and
   free_fair_sched_group() to use alloc_percpu() and free_percpu()
   respectively.

 - Uses the inline accessor tg_cfs_rq(tg, cpu) with per_cpu_ptr() to retrieve
   the pointer to cfs_rq for the given task group and CPU.

 - Replaces direct accesses tg->cfs_rq[cpu] with calls to the new tg_cfs_rq(tg,
   cpu) helper.

 - Handles the root_task_group: since struct rq is already a per-cpu variable
   (runqueues), its embedded cfs_rq (rq->cfs) is also per-cpu. Therefore, we
   assign root_task_group.cfs_rq = &runqueues.cfs.

 - Cleanup the code in initializing the root task group.

This change places each CPU's cfs_rq and sched_entity in its local per-cpu
memory area to remove the per-task_group pointer arrays.

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/20260522141623.600235-4-zli94@ncsu.edu

3 files changed, 45 insertions, 58 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 39cea012c230..dd031410ab1a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8907,7 +8907,7 @@ static struct kmem_cache *task_group_cache __ro_after_init;
 
 void __init sched_init(void)
 {
-	unsigned long ptr = 0;
+	unsigned long __maybe_unused ptr = 0;
 	int i;
 
 	/* Make sure the linker didn't screw up */
@@ -8923,33 +8923,24 @@ void __init sched_init(void)
 	wait_bit_init();
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	ptr += nr_cpu_ids * sizeof(void **);
-#endif
-#ifdef CONFIG_RT_GROUP_SCHED
-	ptr += 2 * nr_cpu_ids * sizeof(void **);
-#endif
-	if (ptr) {
-		ptr = (unsigned long)kzalloc(ptr, GFP_NOWAIT);
+	root_task_group.cfs_rq = &runqueues.cfs;
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-		root_task_group.cfs_rq = (struct cfs_rq **)ptr;
-		ptr += nr_cpu_ids * sizeof(void **);
-
-		root_task_group.shares = ROOT_TASK_GROUP_LOAD;
-		init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
+	root_task_group.shares = ROOT_TASK_GROUP_LOAD;
+	init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_EXT_GROUP_SCHED
-		scx_tg_init(&root_task_group);
+	scx_tg_init(&root_task_group);
 #endif /* CONFIG_EXT_GROUP_SCHED */
 #ifdef CONFIG_RT_GROUP_SCHED
-		root_task_group.rt_se = (struct sched_rt_entity **)ptr;
-		ptr += nr_cpu_ids * sizeof(void **);
+	ptr += 2 * nr_cpu_ids * sizeof(void **);
+	ptr = (unsigned long)kzalloc(ptr, GFP_NOWAIT);
+	root_task_group.rt_se = (struct sched_rt_entity **)ptr;
+	ptr += nr_cpu_ids * sizeof(void **);
 
-		root_task_group.rt_rq = (struct rt_rq **)ptr;
-		ptr += nr_cpu_ids * sizeof(void **);
+	root_task_group.rt_rq = (struct rt_rq **)ptr;
+	ptr += nr_cpu_ids * sizeof(void **);
 
 #endif /* CONFIG_RT_GROUP_SCHED */
-	}
 
 	init_defrootdomain();
 
@@ -9864,7 +9855,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg,
 	}
 
 	for_each_online_cpu(i) {
-		struct cfs_rq *cfs_rq = tg->cfs_rq[i];
+		struct cfs_rq *cfs_rq = tg_cfs_rq(tg, i);
 		struct rq *rq = cfs_rq->rq;
 
 		guard(rq_lock_irq)(rq);
@@ -10032,7 +10023,7 @@ static u64 throttled_time_self(struct task_group *tg)
 	u64 total = 0;
 
 	for_each_possible_cpu(i) {
-		total += READ_ONCE(tg->cfs_rq[i]->throttled_clock_self_time);
+		total += READ_ONCE(tg_cfs_rq(tg, i)->throttled_clock_self_time);
 	}
 
 	return total;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 447b0ac426d1..1d4ed883e630 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -334,7 +334,7 @@ static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 	 * to a tree or when we reach the top of the tree
 	 */
 	if (cfs_rq->tg->parent &&
-	    cfs_rq->tg->parent->cfs_rq[cpu]->on_list) {
+	    tg_cfs_rq(cfs_rq->tg->parent, cpu)->on_list) {
 		/*
 		 * If parent is already on the list, we add the child
 		 * just before. Thanks to circular linked property of
@@ -342,7 +342,7 @@ static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 		 * of the list that starts by parent.
 		 */
 		list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
-			&(cfs_rq->tg->parent->cfs_rq[cpu]->leaf_cfs_rq_list));
+			&(tg_cfs_rq(cfs_rq->tg->parent, cpu)->leaf_cfs_rq_list));
 		/*
 		 * The branch is now connected to its tree so we can
 		 * reset tmp_alone_branch to the beginning of the
@@ -5037,7 +5037,7 @@ static void __maybe_unused clear_tg_offline_cfs_rqs(struct rq *rq)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(tg, &task_groups, list) {
-		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
+		struct cfs_rq *cfs_rq = tg_cfs_rq(tg, cpu_of(rq));
 
 		clear_tg_load_avg(cfs_rq);
 	}
@@ -6594,7 +6594,7 @@ static inline int throttled_hierarchy(struct cfs_rq *cfs_rq)
 
 static inline int lb_throttled_hierarchy(struct task_struct *p, int dst_cpu)
 {
-	return throttled_hierarchy(task_group(p)->cfs_rq[dst_cpu]);
+	return throttled_hierarchy(tg_cfs_rq(task_group(p), dst_cpu));
 }
 
 static inline bool task_is_throttled(struct task_struct *p)
@@ -6740,7 +6740,7 @@ static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags);
 static int tg_unthrottle_up(struct task_group *tg, void *data)
 {
 	struct rq *rq = data;
-	struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
+	struct cfs_rq *cfs_rq = tg_cfs_rq(tg, cpu_of(rq));
 	struct task_struct *p, *tmp;
 
 	if (--cfs_rq->throttle_count)
@@ -6811,7 +6811,7 @@ static void record_throttle_clock(struct cfs_rq *cfs_rq)
 static int tg_throttle_down(struct task_group *tg, void *data)
 {
 	struct rq *rq = data;
-	struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
+	struct cfs_rq *cfs_rq = tg_cfs_rq(tg, cpu_of(rq));
 
 	if (cfs_rq->throttle_count++)
 		return 0;
@@ -7285,8 +7285,8 @@ static void sync_throttle(struct task_group *tg, int cpu)
 	if (!tg->parent)
 		return;
 
-	cfs_rq = tg->cfs_rq[cpu];
-	pcfs_rq = tg->parent->cfs_rq[cpu];
+	cfs_rq = tg_cfs_rq(tg, cpu);
+	pcfs_rq = tg_cfs_rq(tg->parent, cpu);
 
 	cfs_rq->throttle_count = pcfs_rq->throttle_count;
 	cfs_rq->throttled_clock_pelt = rq_clock_pelt(cpu_rq(cpu));
@@ -7478,7 +7478,7 @@ static void __maybe_unused update_runtime_enabled(struct rq *rq)
 	rcu_read_lock();
 	list_for_each_entry_rcu(tg, &task_groups, list) {
 		struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
-		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
+		struct cfs_rq *cfs_rq = tg_cfs_rq(tg, cpu_of(rq));
 
 		raw_spin_lock(&cfs_b->lock);
 		cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF;
@@ -7507,7 +7507,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(tg, &task_groups, list) {
-		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
+		struct cfs_rq *cfs_rq = tg_cfs_rq(tg, cpu_of(rq));
 
 		if (!cfs_rq->runtime_enabled)
 			continue;
@@ -10382,7 +10382,7 @@ static inline int task_is_ineligible_on_dst_cpu(struct task_struct *p, int dest_
 	struct cfs_rq *dst_cfs_rq;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	dst_cfs_rq = task_group(p)->cfs_rq[dest_cpu];
+	dst_cfs_rq = tg_cfs_rq(task_group(p), dest_cpu);
 #else
 	dst_cfs_rq = &cpu_rq(dest_cpu)->cfs;
 #endif
@@ -14812,7 +14812,7 @@ static int task_is_throttled_fair(struct task_struct *p, int cpu)
 	struct cfs_rq *cfs_rq;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	cfs_rq = task_group(p)->cfs_rq[cpu];
+	cfs_rq = tg_cfs_rq(task_group(p), cpu);
 #else
 	cfs_rq = &cpu_rq(cpu)->cfs;
 #endif
@@ -15076,39 +15076,31 @@ static void task_change_group_fair(struct task_struct *p)
 
 void free_fair_sched_group(struct task_group *tg)
 {
-	int i;
-
-	for_each_possible_cpu(i) {
-		if (tg->cfs_rq)
-			kfree(tg->cfs_rq[i]);
-	}
-
-	kfree(tg->cfs_rq);
+	free_percpu(tg->cfs_rq);
 }
 
 int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 {
-	struct cfs_tg_state *state;
+	struct cfs_tg_state __percpu *state;
 	struct sched_entity *se;
 	struct cfs_rq *cfs_rq;
 	int i;
 
-	tg->cfs_rq = kzalloc_objs(cfs_rq, nr_cpu_ids);
-	if (!tg->cfs_rq)
+	state = alloc_percpu_gfp(struct cfs_tg_state, GFP_KERNEL);
+	if (!state)
 		goto err;
 
+	tg->cfs_rq = &state->cfs_rq;
 	tg->shares = NICE_0_LOAD;
 
 	init_cfs_bandwidth(tg_cfs_bandwidth(tg), tg_cfs_bandwidth(parent));
 
 	for_each_possible_cpu(i) {
-		state = kzalloc_node(sizeof(*state),
-				     GFP_KERNEL, cpu_to_node(i));
-		if (!state)
+		cfs_rq = tg_cfs_rq(tg, i);
+		if (!cfs_rq)
 			goto err;
 
-		cfs_rq = &state->cfs_rq;
-		se = &state->se;
+		se = tg_se(tg, i);
 		init_cfs_rq(cfs_rq);
 		init_tg_cfs_entry(tg, cfs_rq, se, i, tg_se(parent, i));
 		init_entity_runnable_average(se);
@@ -15145,7 +15137,7 @@ void unregister_fair_sched_group(struct task_group *tg)
 	destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));
 
 	for_each_possible_cpu(cpu) {
-		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu];
+		struct cfs_rq *cfs_rq = tg_cfs_rq(tg, cpu);
 		struct sched_entity *se = tg_se(tg, cpu);
 		struct rq *rq = cpu_rq(cpu);
 
@@ -15182,8 +15174,6 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 	cfs_rq->rq = rq;
 	init_cfs_rq_runtime(cfs_rq);
 
-	tg->cfs_rq[cpu] = cfs_rq;
-
 	/* se could be NULL for root_task_group */
 	if (!se)
 		return;
@@ -15276,7 +15266,7 @@ 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(tg, i);
-		struct cfs_rq *grp_cfs_rq = tg->cfs_rq[i];
+		struct cfs_rq *grp_cfs_rq = tg_cfs_rq(tg, i);
 		bool was_idle = cfs_rq_is_idle(grp_cfs_rq);
 		long idle_task_delta;
 		struct rq_flags rf;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 823ba40cf098..c7c2dea65edd 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -485,7 +485,7 @@ struct task_group {
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* runqueue "owned" by this group on each CPU */
-	struct cfs_rq		**cfs_rq;
+	struct cfs_rq __percpu	*cfs_rq;
 	unsigned long		shares;
 	/*
 	 * load_avg can be heavily contended at clock tick time, so put
@@ -2304,6 +2304,12 @@ struct cfs_tg_state {
 	struct sched_statistics	stats;
 } __no_randomize_layout;
 
+/* Access a specific CPU's cfs_rq from a task group */
+static inline struct cfs_rq *tg_cfs_rq(struct task_group *tg, int cpu)
+{
+	return per_cpu_ptr(tg->cfs_rq, cpu);
+}
+
 static inline struct sched_entity *tg_se(struct task_group *tg, int cpu)
 {
 	struct cfs_tg_state *state;
@@ -2311,7 +2317,7 @@ static inline struct sched_entity *tg_se(struct task_group *tg, int cpu)
 	if (is_root_task_group(tg))
 		return NULL;
 
-	state = container_of(tg->cfs_rq[cpu], struct cfs_tg_state, cfs_rq);
+	state = container_of(tg_cfs_rq(tg, cpu), struct cfs_tg_state, cfs_rq);
 	return &state->se;
 }
 
@@ -2335,8 +2341,8 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 #endif
 
 #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];
+	set_task_rq_fair(&p->se, p->se.cfs_rq, tg_cfs_rq(tg, cpu));
+	p->se.cfs_rq = tg_cfs_rq(tg, cpu);
 	p->se.parent = tg_se(tg, cpu);
 	p->se.depth = p->se.parent ? p->se.parent->depth + 1 : 0;
 #endif