sched_ext: Add cgroup support

Add sched_ext_ops operations to init/exit cgroups, and track task migrations
and config changes. A BPF scheduler may not implement or implement only
subset of cgroup features. The implemented features can be indicated using
%SCX_OPS_HAS_CGOUP_* flags. If cgroup configuration makes use of features
that are not implemented, a warning is triggered.

While a BPF scheduler is being enabled and disabled, relevant cgroup
operations are locked out using scx_cgroup_rwsem. This avoids situations
like task prep taking place while the task is being moved across cgroups,
making things easier for BPF schedulers.

v7: - cgroup interface file visibility toggling is dropped in favor just
      warning messages. Dynamically changing interface visiblity caused more
      confusion than helping.

v6: - Updated to reflect the removal of SCX_KF_SLEEPABLE.

    - Updated to use CONFIG_GROUP_SCHED_WEIGHT and fixes for
      !CONFIG_FAIR_GROUP_SCHED && CONFIG_EXT_GROUP_SCHED.

v5: - Flipped the locking order between scx_cgroup_rwsem and
      cpus_read_lock() to avoid locking order conflict w/ cpuset. Better
      documentation around locking.

    - sched_move_task() takes an early exit if the source and destination
      are identical. This triggered the warning in scx_cgroup_can_attach()
      as it left p->scx.cgrp_moving_from uncleared. Updated the cgroup
      migration path so that ops.cgroup_prep_move() is skipped for identity
      migrations so that its invocations always match ops.cgroup_move()
      one-to-one.

v4: - Example schedulers moved into their own patches.

    - Fix build failure when !CONFIG_CGROUP_SCHED, reported by Andrea Righi.

v3: - Make scx_example_pair switch all tasks by default.

    - Convert to BPF inline iterators.

    - scx_bpf_task_cgroup() is added to determine the current cgroup from
      CPU controller's POV. This allows BPF schedulers to accurately track
      CPU cgroup membership.

    - scx_example_flatcg added. This demonstrates flattened hierarchy
      implementation of CPU cgroup control and shows significant performance
      improvement when cgroups which are nested multiple levels are under
      competition.

v2: - Build fixes for different CONFIG combinations.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: David Vernet <dvernet@meta.com>
Acked-by: Josh Don <joshdon@google.com>
Acked-by: Hao Luo <haoluo@google.com>
Acked-by: Barret Rhoden <brho@google.com>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Andrea Righi <andrea.righi@canonical.com>

include/linux/sched/ext.h

@@ -188,6 +188,9 @@ struct sched_ext_entity {
 	bool			disallow;	/* reject switching into SCX */
 
 	/* cold fields */
+#ifdef CONFIG_EXT_GROUP_SCHED
+	struct cgroup		*cgrp_moving_from;
+#endif
 	/* must be the last field, see init_scx_entity() */
 	struct list_head	tasks_node;
 };

init/Kconfig

@@ -1055,6 +1055,12 @@ config RT_GROUP_SCHED
 	  realtime bandwidth for them.
 	  See Documentation/scheduler/sched-rt-group.rst for more information.
 
+config EXT_GROUP_SCHED
+	bool
+	depends on SCHED_CLASS_EXT && CGROUP_SCHED
+	select GROUP_SCHED_WEIGHT
+	default y
+
 endif #CGROUP_SCHED
 
 config SCHED_MM_CID

kernel/sched/core.c

@@ -8364,6 +8364,9 @@ void __init sched_init(void)
 		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
+		root_task_group.scx_weight = CGROUP_WEIGHT_DFL;
+#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 **);
@@ -8801,6 +8804,7 @@ struct task_group *sched_create_group(struct task_group *parent)
 	if (!alloc_rt_sched_group(tg, parent))
 		goto err;
 
+	scx_group_set_weight(tg, CGROUP_WEIGHT_DFL);
 	alloc_uclamp_sched_group(tg, parent);
 
 	return tg;
@@ -8928,6 +8932,7 @@ void sched_move_task(struct task_struct *tsk)
 		put_prev_task(rq, tsk);
 
 	sched_change_group(tsk, group);
+	scx_move_task(tsk);
 
 	if (queued)
 		enqueue_task(rq, tsk, queue_flags);
@@ -8965,6 +8970,11 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
 {
 	struct task_group *tg = css_tg(css);
 	struct task_group *parent = css_tg(css->parent);
+	int ret;
+
+	ret = scx_tg_online(tg);
+	if (ret)
+		return ret;
 
 	if (parent)
 		sched_online_group(tg, parent);
@@ -8979,6 +8989,13 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
 	return 0;
 }
 
+static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
+{
+	struct task_group *tg = css_tg(css);
+
+	scx_tg_offline(tg);
+}
+
 static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
 {
 	struct task_group *tg = css_tg(css);
@@ -8996,9 +9013,9 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
 	sched_unregister_group(tg);
 }
 
-#ifdef CONFIG_RT_GROUP_SCHED
 static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 {
+#ifdef CONFIG_RT_GROUP_SCHED
 	struct task_struct *task;
 	struct cgroup_subsys_state *css;
 
@@ -9006,9 +9023,9 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 		if (!sched_rt_can_attach(css_tg(css), task))
 			return -EINVAL;
 	}
-	return 0;
-}
 #endif
+	return scx_cgroup_can_attach(tset);
+}
 
 static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 {
@@ -9017,6 +9034,13 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 
 	cgroup_taskset_for_each(task, css, tset)
 		sched_move_task(task);
+
+	scx_cgroup_finish_attach();
+}
+
+static void cpu_cgroup_cancel_attach(struct cgroup_taskset *tset)
+{
+	scx_cgroup_cancel_attach(tset);
 }
 
 #ifdef CONFIG_UCLAMP_TASK_GROUP
@@ -9196,15 +9220,25 @@ static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
 #ifdef CONFIG_GROUP_SCHED_WEIGHT
 static unsigned long tg_weight(struct task_group *tg)
 {
+#ifdef CONFIG_FAIR_GROUP_SCHED
 	return scale_load_down(tg->shares);
+#else
+	return sched_weight_from_cgroup(tg->scx_weight);
+#endif
 }
 
 static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
 				struct cftype *cftype, u64 shareval)
 {
+	int ret;
+
 	if (shareval > scale_load_down(ULONG_MAX))
 		shareval = MAX_SHARES;
-	return sched_group_set_shares(css_tg(css), scale_load(shareval));
+	ret = sched_group_set_shares(css_tg(css), scale_load(shareval));
+	if (!ret)
+		scx_group_set_weight(css_tg(css),
+				     sched_weight_to_cgroup(shareval));
+	return ret;
 }
 
 static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
@@ -9595,7 +9629,12 @@ static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css,
 static int cpu_idle_write_s64(struct cgroup_subsys_state *css,
 				struct cftype *cft, s64 idle)
 {
-	return sched_group_set_idle(css_tg(css), idle);
+	int ret;
+
+	ret = sched_group_set_idle(css_tg(css), idle);
+	if (!ret)
+		scx_group_set_idle(css_tg(css), idle);
+	return ret;
 }
 #endif
 
@@ -9722,13 +9761,17 @@ static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
 				struct cftype *cft, u64 cgrp_weight)
 {
 	unsigned long weight;
+	int ret;
 
 	if (cgrp_weight < CGROUP_WEIGHT_MIN || cgrp_weight > CGROUP_WEIGHT_MAX)
 		return -ERANGE;
 
 	weight = sched_weight_from_cgroup(cgrp_weight);
 
-	return sched_group_set_shares(css_tg(css), scale_load(weight));
+	ret = sched_group_set_shares(css_tg(css), scale_load(weight));
+	if (!ret)
+		scx_group_set_weight(css_tg(css), cgrp_weight);
+	return ret;
 }
 
 static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
@@ -9753,7 +9796,7 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
 				     struct cftype *cft, s64 nice)
 {
 	unsigned long weight;
-	int idx;
+	int idx, ret;
 
 	if (nice < MIN_NICE || nice > MAX_NICE)
 		return -ERANGE;
@@ -9762,7 +9805,11 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
 	idx = array_index_nospec(idx, 40);
 	weight = sched_prio_to_weight[idx];
 
-	return sched_group_set_shares(css_tg(css), scale_load(weight));
+	ret = sched_group_set_shares(css_tg(css), scale_load(weight));
+	if (!ret)
+		scx_group_set_weight(css_tg(css),
+				     sched_weight_to_cgroup(weight));
+	return ret;
 }
 #endif /* CONFIG_GROUP_SCHED_WEIGHT */
 
@@ -9878,14 +9925,14 @@ static struct cftype cpu_files[] = {
 struct cgroup_subsys cpu_cgrp_subsys = {
 	.css_alloc	= cpu_cgroup_css_alloc,
 	.css_online	= cpu_cgroup_css_online,
+	.css_offline	= cpu_cgroup_css_offline,
 	.css_released	= cpu_cgroup_css_released,
 	.css_free	= cpu_cgroup_css_free,
 	.css_extra_stat_show = cpu_extra_stat_show,
 	.css_local_stat_show = cpu_local_stat_show,
-#ifdef CONFIG_RT_GROUP_SCHED
 	.can_attach	= cpu_cgroup_can_attach,
-#endif
 	.attach		= cpu_cgroup_attach,
+	.cancel_attach	= cpu_cgroup_cancel_attach,
 	.legacy_cftypes	= cpu_legacy_files,
 	.dfl_cftypes	= cpu_files,
 	.early_init	= true,

kernel/sched/ext.h

@@ -67,3 +67,25 @@ static inline void scx_update_idle(struct rq *rq, bool idle)
 #else
 static inline void scx_update_idle(struct rq *rq, bool idle) {}
 #endif
+
+#ifdef CONFIG_CGROUP_SCHED
+#ifdef CONFIG_EXT_GROUP_SCHED
+int scx_tg_online(struct task_group *tg);
+void scx_tg_offline(struct task_group *tg);
+int scx_cgroup_can_attach(struct cgroup_taskset *tset);
+void scx_move_task(struct task_struct *p);
+void scx_cgroup_finish_attach(void);
+void scx_cgroup_cancel_attach(struct cgroup_taskset *tset);
+void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight);
+void scx_group_set_idle(struct task_group *tg, bool idle);
+#else	/* CONFIG_EXT_GROUP_SCHED */
+static inline int scx_tg_online(struct task_group *tg) { return 0; }
+static inline void scx_tg_offline(struct task_group *tg) {}
+static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; }
+static inline void scx_move_task(struct task_struct *p) {}
+static inline void scx_cgroup_finish_attach(void) {}
+static inline void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) {}
+static inline void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight) {}
+static inline void scx_group_set_idle(struct task_group *tg, bool idle) {}
+#endif	/* CONFIG_EXT_GROUP_SCHED */
+#endif	/* CONFIG_CGROUP_SCHED */

kernel/sched/sched.h

@@ -459,6 +459,11 @@ struct task_group {
 	struct rt_bandwidth	rt_bandwidth;
 #endif
 
+#ifdef CONFIG_EXT_GROUP_SCHED
+	u32			scx_flags;	/* SCX_TG_* */
+	u32			scx_weight;
+#endif
+
 	struct rcu_head		rcu;
 	struct list_head	list;
 

tools/sched_ext/include/scx/common.bpf.h

@@ -61,6 +61,7 @@ s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym;
 bool scx_bpf_task_running(const struct task_struct *p) __ksym;
 s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym;
 struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym;
+struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) __ksym;
 
 static inline __attribute__((format(printf, 1, 2)))
 void ___scx_bpf_bstr_format_checker(const char *fmt, ...) {}

tools/testing/selftests/sched_ext/maximal.bpf.c

@@ -95,6 +95,32 @@ void BPF_STRUCT_OPS(maximal_exit_task, struct task_struct *p,
 void BPF_STRUCT_OPS(maximal_disable, struct task_struct *p)
 {}
 
+s32 BPF_STRUCT_OPS(maximal_cgroup_init, struct cgroup *cgrp,
+		   struct scx_cgroup_init_args *args)
+{
+	return 0;
+}
+
+void BPF_STRUCT_OPS(maximal_cgroup_exit, struct cgroup *cgrp)
+{}
+
+s32 BPF_STRUCT_OPS(maximal_cgroup_prep_move, struct task_struct *p,
+		   struct cgroup *from, struct cgroup *to)
+{
+	return 0;
+}
+
+void BPF_STRUCT_OPS(maximal_cgroup_move, struct task_struct *p,
+		    struct cgroup *from, struct cgroup *to)
+{}
+
+void BPF_STRUCT_OPS(maximal_cgroup_cancel_move, struct task_struct *p,
+	       struct cgroup *from, struct cgroup *to)
+{}
+
+void BPF_STRUCT_OPS(maximal_cgroup_set_weight, struct cgroup *cgrp, u32 weight)
+{}
+
 s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init)
 {
 	return 0;
@@ -126,6 +152,12 @@ struct sched_ext_ops maximal_ops = {
 	.enable			= maximal_enable,
 	.exit_task		= maximal_exit_task,
 	.disable		= maximal_disable,
+	.cgroup_init		= maximal_cgroup_init,
+	.cgroup_exit		= maximal_cgroup_exit,
+	.cgroup_prep_move	= maximal_cgroup_prep_move,
+	.cgroup_move		= maximal_cgroup_move,
+	.cgroup_cancel_move	= maximal_cgroup_cancel_move,
+	.cgroup_set_weight	= maximal_cgroup_set_weight,
 	.init			= maximal_init,
 	.exit			= maximal_exit,
 	.name			= "maximal",