Merge tag 'sched_ext-for-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext

Pull sched_ext support from Tejun Heo:
 "This implements a new scheduler class called ‘ext_sched_class’, or
  sched_ext, which allows scheduling policies to be implemented as BPF
  programs.

  The goals of this are:

   - Ease of experimentation and exploration: Enabling rapid iteration
     of new scheduling policies.

   - Customization: Building application-specific schedulers which
     implement policies that are not applicable to general-purpose
     schedulers.

   - Rapid scheduler deployments: Non-disruptive swap outs of scheduling
     policies in production environments"

See individual commits for more documentation, but also the cover letter
for the latest series:

Link: https://lore.kernel.org/all/20240618212056.2833381-1-tj@kernel.org/

* tag 'sched_ext-for-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext: (110 commits)
  sched: Move update_other_load_avgs() to kernel/sched/pelt.c
  sched_ext: Don't trigger ops.quiescent/runnable() on migrations
  sched_ext: Synchronize bypass state changes with rq lock
  scx_qmap: Implement highpri boosting
  sched_ext: Implement scx_bpf_dispatch[_vtime]_from_dsq()
  sched_ext: Compact struct bpf_iter_scx_dsq_kern
  sched_ext: Replace consume_local_task() with move_local_task_to_local_dsq()
  sched_ext: Move consume_local_task() upward
  sched_ext: Move sanity check and dsq_mod_nr() into task_unlink_from_dsq()
  sched_ext: Reorder args for consume_local/remote_task()
  sched_ext: Restructure dispatch_to_local_dsq()
  sched_ext: Fix processs_ddsp_deferred_locals() by unifying DTL_INVALID handling
  sched_ext: Make find_dsq_for_dispatch() handle SCX_DSQ_LOCAL_ON
  sched_ext: Refactor consume_remote_task()
  sched_ext: Rename scx_kfunc_set_sleepable to unlocked and relocate
  sched_ext: Add missing static to scx_dump_data
  sched_ext: Add missing static to scx_has_op[]
  sched_ext: Temporarily work around pick_task_scx() being called without balance_scx()
  sched_ext: Add a cgroup scheduler which uses flattened hierarchy
  sched_ext: Add cgroup support
  ...

14 files changed, 7774 insertions, 122 deletions

diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index c2f1fd95a821..fe782cd77388 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -133,4 +133,29 @@ config SCHED_CORE
 	  which is the likely usage by Linux distributions, there should
 	  be no measurable impact on performance.
 
-
+config SCHED_CLASS_EXT
+	bool "Extensible Scheduling Class"
+	depends on BPF_SYSCALL && BPF_JIT && DEBUG_INFO_BTF
+	select STACKTRACE if STACKTRACE_SUPPORT
+	help
+	  This option enables a new scheduler class sched_ext (SCX), which
+	  allows scheduling policies to be implemented as BPF programs to
+	  achieve the following:
+
+	  - Ease of experimentation and exploration: Enabling rapid
+	    iteration of new scheduling policies.
+	  - Customization: Building application-specific schedulers which
+	    implement policies that are not applicable to general-purpose
+	    schedulers.
+	  - Rapid scheduler deployments: Non-disruptive swap outs of
+	    scheduling policies in production environments.
+
+	  sched_ext leverages BPF struct_ops feature to define a structure
+	  which exports function callbacks and flags to BPF programs that
+	  wish to implement scheduling policies. The struct_ops structure
+	  exported by sched_ext is struct sched_ext_ops, and is conceptually
+	  similar to struct sched_class.
+
+	  For more information:
+	    Documentation/scheduler/sched-ext.rst
+	    https://github.com/sched-ext/scx
diff --git a/kernel/fork.c b/kernel/fork.c
index 5ac41db8aa69..cbdaca45d0c1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -23,6 +23,7 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/ext.h>
 #include <linux/seq_file.h>
 #include <linux/rtmutex.h>
 #include <linux/init.h>
@@ -969,6 +970,7 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(refcount_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
+	sched_ext_free(tsk);
 	io_uring_free(tsk);
 	cgroup_free(tsk);
 	task_numa_free(tsk, true);
@@ -2346,7 +2348,7 @@ __latent_entropy struct task_struct *copy_process(
 
 	retval = perf_event_init_task(p, clone_flags);
 	if (retval)
-		goto bad_fork_cleanup_policy;
+		goto bad_fork_sched_cancel_fork;
 	retval = audit_alloc(p);
 	if (retval)
 		goto bad_fork_cleanup_perf;
@@ -2479,7 +2481,9 @@ __latent_entropy struct task_struct *copy_process(
 	 * cgroup specific, it unconditionally needs to place the task on a
 	 * runqueue.
 	 */
-	sched_cgroup_fork(p, args);
+	retval = sched_cgroup_fork(p, args);
+	if (retval)
+		goto bad_fork_cancel_cgroup;
 
 	/*
 	 * From this point on we must avoid any synchronous user-space
@@ -2525,13 +2529,13 @@ __latent_entropy struct task_struct *copy_process(
 	/* Don't start children in a dying pid namespace */
 	if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) {
 		retval = -ENOMEM;
-		goto bad_fork_cancel_cgroup;
+		goto bad_fork_core_free;
 	}
 
 	/* Let kill terminate clone/fork in the middle */
 	if (fatal_signal_pending(current)) {
 		retval = -EINTR;
-		goto bad_fork_cancel_cgroup;
+		goto bad_fork_core_free;
 	}
 
 	/* No more failure paths after this point. */
@@ -2605,10 +2609,11 @@ __latent_entropy struct task_struct *copy_process(
 
 	return p;
 
-bad_fork_cancel_cgroup:
+bad_fork_core_free:
 	sched_core_free(p);
 	spin_unlock(&current->sighand->siglock);
 	write_unlock_irq(&tasklist_lock);
+bad_fork_cancel_cgroup:
 	cgroup_cancel_fork(p, args);
 bad_fork_put_pidfd:
 	if (clone_flags & CLONE_PIDFD) {
@@ -2647,6 +2652,8 @@ bad_fork_cleanup_audit:
 	audit_free(p);
 bad_fork_cleanup_perf:
 	perf_event_free_task(p);
+bad_fork_sched_cancel_fork:
+	sched_cancel_fork(p);
 bad_fork_cleanup_policy:
 	lockdep_free_task(p);
 #ifdef CONFIG_NUMA
diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c
index 39c315182b35..fae1f5c921eb 100644
--- a/kernel/sched/build_policy.c
+++ b/kernel/sched/build_policy.c
@@ -16,18 +16,25 @@
 #include <linux/sched/clock.h>
 #include <linux/sched/cputime.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/isolation.h>
 #include <linux/sched/posix-timers.h>
 #include <linux/sched/rt.h>
 
 #include <linux/cpuidle.h>
 #include <linux/jiffies.h>
+#include <linux/kobject.h>
 #include <linux/livepatch.h>
+#include <linux/pm.h>
 #include <linux/psi.h>
+#include <linux/rhashtable.h>
+#include <linux/seq_buf.h>
 #include <linux/seqlock_api.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
 #include <linux/tsacct_kern.h>
 #include <linux/vtime.h>
+#include <linux/sysrq.h>
+#include <linux/percpu-rwsem.h>
 
 #include <uapi/linux/sched/types.h>
 
@@ -52,4 +59,8 @@
 #include "cputime.c"
 #include "deadline.c"
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+# include "ext.c"
+#endif
+
 #include "syscalls.c"
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c1a08035ea43..b6cc1cf499d6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -172,7 +172,10 @@ static inline int __task_prio(const struct task_struct *p)
 	if (p->sched_class == &idle_sched_class)
 		return MAX_RT_PRIO + NICE_WIDTH; /* 140 */
 
-	return MAX_RT_PRIO + MAX_NICE; /* 120, squash fair */
+	if (task_on_scx(p))
+		return MAX_RT_PRIO + MAX_NICE + 1; /* 120, squash ext */
+
+	return MAX_RT_PRIO + MAX_NICE; /* 119, squash fair */
 }
 
 /*
@@ -217,6 +220,11 @@ static inline bool prio_less(const struct task_struct *a,
 	if (pa == MAX_RT_PRIO + MAX_NICE)	/* fair */
 		return cfs_prio_less(a, b, in_fi);
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+	if (pa == MAX_RT_PRIO + MAX_NICE + 1)	/* ext */
+		return scx_prio_less(a, b, in_fi);
+#endif
+
 	return false;
 }
 
@@ -1280,11 +1288,14 @@ bool sched_can_stop_tick(struct rq *rq)
 		return true;
 
 	/*
-	 * If there are no DL,RR/FIFO tasks, there must only be CFS tasks left;
-	 * if there's more than one we need the tick for involuntary
-	 * preemption.
+	 * If there are no DL,RR/FIFO tasks, there must only be CFS or SCX tasks
+	 * left. For CFS, if there's more than one we need the tick for
+	 * involuntary preemption. For SCX, ask.
 	 */
-	if (rq->nr_running > 1)
+	if (scx_enabled() && !scx_can_stop_tick(rq))
+		return false;
+
+	if (rq->cfs.nr_running > 1)
 		return false;
 
 	/*
@@ -1366,8 +1377,8 @@ void set_load_weight(struct task_struct *p, bool update_load)
 	 * SCHED_OTHER tasks have to update their load when changing their
 	 * weight
 	 */
-	if (update_load && p->sched_class == &fair_sched_class)
-		reweight_task(p, &lw);
+	if (update_load && p->sched_class->reweight_task)
+		p->sched_class->reweight_task(task_rq(p), p, &lw);
 	else
 		p->se.load = lw;
 }
@@ -2087,6 +2098,17 @@ inline int task_curr(const struct task_struct *p)
 }
 
 /*
+ * ->switching_to() is called with the pi_lock and rq_lock held and must not
+ * mess with locking.
+ */
+void check_class_changing(struct rq *rq, struct task_struct *p,
+			  const struct sched_class *prev_class)
+{
+	if (prev_class != p->sched_class && p->sched_class->switching_to)
+		p->sched_class->switching_to(rq, p);
+}
+
+/*
  * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock,
  * use the balance_callback list if you want balancing.
  *
@@ -2356,7 +2378,7 @@ static inline bool rq_has_pinned_tasks(struct rq *rq)
 static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
 {
 	/* When not in the task's cpumask, no point in looking further. */
-	if (!cpumask_test_cpu(cpu, p->cpus_ptr))
+	if (!task_allowed_on_cpu(p, cpu))
 		return false;
 
 	/* migrate_disabled() must be allowed to finish. */
@@ -2365,7 +2387,7 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
 
 	/* Non kernel threads are not allowed during either online or offline. */
 	if (!(p->flags & PF_KTHREAD))
-		return cpu_active(cpu) && task_cpu_possible(cpu, p);
+		return cpu_active(cpu);
 
 	/* KTHREAD_IS_PER_CPU is always allowed. */
 	if (kthread_is_per_cpu(p))
@@ -3843,6 +3865,15 @@ bool cpus_share_resources(int this_cpu, int that_cpu)
 static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
 {
 	/*
+	 * The BPF scheduler may depend on select_task_rq() being invoked during
+	 * wakeups. In addition, @p may end up executing on a different CPU
+	 * regardless of what happens in the wakeup path making the ttwu_queue
+	 * optimization less meaningful. Skip if on SCX.
+	 */
+	if (task_on_scx(p))
+		return false;
+
+	/*
 	 * Do not complicate things with the async wake_list while the CPU is
 	 * in hotplug state.
 	 */
@@ -4416,6 +4447,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->rt.on_rq		= 0;
 	p->rt.on_list		= 0;
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+	init_scx_entity(&p->scx);
+#endif
+
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
 #endif
@@ -4658,10 +4693,18 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 	if (dl_prio(p->prio))
 		return -EAGAIN;
-	else if (rt_prio(p->prio))
+
+	scx_pre_fork(p);
+
+	if (rt_prio(p->prio)) {
 		p->sched_class = &rt_sched_class;
-	else
+#ifdef CONFIG_SCHED_CLASS_EXT
+	} else if (task_should_scx(p)) {
+		p->sched_class = &ext_sched_class;
+#endif
+	} else {
 		p->sched_class = &fair_sched_class;
+	}
 
 	init_entity_runnable_average(&p->se);
 
@@ -4681,7 +4724,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	return 0;
 }
 
-void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
+int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
 {
 	unsigned long flags;
 
@@ -4708,11 +4751,19 @@ void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
+	return scx_fork(p);
+}
+
+void sched_cancel_fork(struct task_struct *p)
+{
+	scx_cancel_fork(p);
 }
 
 void sched_post_fork(struct task_struct *p)
 {
 	uclamp_post_fork(p);
+	scx_post_fork(p);
 }
 
 unsigned long to_ratio(u64 period, u64 runtime)
@@ -5545,6 +5596,7 @@ void sched_tick(void)
 	calc_global_load_tick(rq);
 	sched_core_tick(rq);
 	task_tick_mm_cid(rq, curr);
+	scx_tick(rq);
 
 	rq_unlock(rq, &rf);
 
@@ -5557,8 +5609,10 @@ void sched_tick(void)
 		wq_worker_tick(curr);
 
 #ifdef CONFIG_SMP
-	rq->idle_balance = idle_cpu(cpu);
-	sched_balance_trigger(rq);
+	if (!scx_switched_all()) {
+		rq->idle_balance = idle_cpu(cpu);
+		sched_balance_trigger(rq);
+	}
 #endif
 }
 
@@ -5848,8 +5902,19 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt)
 static void prev_balance(struct rq *rq, struct task_struct *prev,
 			 struct rq_flags *rf)
 {
-#ifdef CONFIG_SMP
+	const struct sched_class *start_class = prev->sched_class;
 	const struct sched_class *class;
+
+#ifdef CONFIG_SCHED_CLASS_EXT
+	/*
+	 * SCX requires a balance() call before every pick_next_task() including
+	 * when waking up from SCHED_IDLE. If @start_class is below SCX, start
+	 * from SCX instead.
+	 */
+	if (scx_enabled() && sched_class_above(&ext_sched_class, start_class))
+		start_class = &ext_sched_class;
+#endif
+
 	/*
 	 * We must do the balancing pass before put_prev_task(), such
 	 * that when we release the rq->lock the task is in the same
@@ -5858,11 +5923,10 @@ static void prev_balance(struct rq *rq, struct task_struct *prev,
 	 * We can terminate the balance pass as soon as we know there is
 	 * a runnable task of @class priority or higher.
 	 */
-	for_class_range(class, prev->sched_class, &idle_sched_class) {
-		if (class->balance(rq, prev, rf))
+	for_active_class_range(class, start_class, &idle_sched_class) {
+		if (class->balance && class->balance(rq, prev, rf))
 			break;
 	}
-#endif
 }
 
 /*
@@ -5876,6 +5940,9 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	rq->dl_server = NULL;
 
+	if (scx_enabled())
+		goto restart;
+
 	/*
 	 * Optimization: we know that if all tasks are in the fair class we can
 	 * call that function directly, but only if the @prev task wasn't of a
@@ -5901,7 +5968,7 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 restart:
 	prev_balance(rq, prev, rf);
 
-	for_each_class(class) {
+	for_each_active_class(class) {
 		if (class->pick_next_task) {
 			p = class->pick_next_task(rq, prev);
 			if (p)
@@ -5944,7 +6011,7 @@ static inline struct task_struct *pick_task(struct rq *rq)
 
 	rq->dl_server = NULL;
 
-	for_each_class(class) {
+	for_each_active_class(class) {
 		p = class->pick_task(rq);
 		if (p)
 			return p;
@@ -6948,6 +7015,10 @@ void __setscheduler_prio(struct task_struct *p, int prio)
 		p->sched_class = &dl_sched_class;
 	else if (rt_prio(prio))
 		p->sched_class = &rt_sched_class;
+#ifdef CONFIG_SCHED_CLASS_EXT
+	else if (task_should_scx(p))
+		p->sched_class = &ext_sched_class;
+#endif
 	else
 		p->sched_class = &fair_sched_class;
 
@@ -7093,6 +7164,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	}
 
 	__setscheduler_prio(p, prio);
+	check_class_changing(rq, p, prev_class);
 
 	if (queued)
 		enqueue_task(rq, p, queue_flag);
@@ -7505,6 +7577,7 @@ void sched_show_task(struct task_struct *p)
 
 	print_worker_info(KERN_INFO, p);
 	print_stop_info(KERN_INFO, p);
+	print_scx_info(KERN_INFO, p);
 	show_stack(p, NULL, KERN_INFO);
 	put_task_stack(p);
 }
@@ -8033,6 +8106,8 @@ int sched_cpu_activate(unsigned int cpu)
 		cpuset_cpu_active();
 	}
 
+	scx_rq_activate(rq);
+
 	/*
 	 * Put the rq online, if not already. This happens:
 	 *
@@ -8082,6 +8157,8 @@ int sched_cpu_deactivate(unsigned int cpu)
 
 	sched_set_rq_offline(rq, cpu);
 
+	scx_rq_deactivate(rq);
+
 	/*
 	 * When going down, decrement the number of cores with SMT present.
 	 */
@@ -8266,11 +8343,15 @@ void __init sched_init(void)
 	int i;
 
 	/* Make sure the linker didn't screw up */
-	BUG_ON(&idle_sched_class != &fair_sched_class + 1 ||
-	       &fair_sched_class != &rt_sched_class + 1 ||
-	       &rt_sched_class   != &dl_sched_class + 1);
 #ifdef CONFIG_SMP
-	BUG_ON(&dl_sched_class != &stop_sched_class + 1);
+	BUG_ON(!sched_class_above(&stop_sched_class, &dl_sched_class));
+#endif
+	BUG_ON(!sched_class_above(&dl_sched_class, &rt_sched_class));
+	BUG_ON(!sched_class_above(&rt_sched_class, &fair_sched_class));
+	BUG_ON(!sched_class_above(&fair_sched_class, &idle_sched_class));
+#ifdef CONFIG_SCHED_CLASS_EXT
+	BUG_ON(!sched_class_above(&fair_sched_class, &ext_sched_class));
+	BUG_ON(!sched_class_above(&ext_sched_class, &idle_sched_class));
 #endif
 
 	wait_bit_init();
@@ -8294,6 +8375,9 @@ 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 **);
@@ -8445,6 +8529,7 @@ void __init sched_init(void)
 	balance_push_set(smp_processor_id(), false);
 #endif
 	init_sched_fair_class();
+	init_sched_ext_class();
 
 	psi_init();
 
@@ -8730,6 +8815,7 @@ 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;
@@ -8857,6 +8943,7 @@ 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);
@@ -8871,11 +8958,6 @@ void sched_move_task(struct task_struct *tsk)
 	}
 }
 
-static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
-{
-	return css ? container_of(css, struct task_group, css) : NULL;
-}
-
 static struct cgroup_subsys_state *
 cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 {
@@ -8899,6 +8981,11 @@ 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);
@@ -8913,6 +9000,13 @@ 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);
@@ -8930,9 +9024,9 @@ 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;
 
@@ -8940,9 +9034,9 @@ 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)
 {
@@ -8951,6 +9045,13 @@ 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
@@ -9127,22 +9228,36 @@ static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
 }
 #endif /* CONFIG_UCLAMP_TASK_GROUP */
 
+#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,
 			       struct cftype *cft)
 {
-	struct task_group *tg = css_tg(css);
-
-	return (u64) scale_load_down(tg->shares);
+	return tg_weight(css_tg(css));
 }
+#endif /* CONFIG_GROUP_SCHED_WEIGHT */
 
 #ifdef CONFIG_CFS_BANDWIDTH
 static DEFINE_MUTEX(cfs_constraints_mutex);
@@ -9488,7 +9603,6 @@ static int cpu_cfs_local_stat_show(struct seq_file *sf, void *v)
 	return 0;
 }
 #endif /* CONFIG_CFS_BANDWIDTH */
-#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #ifdef CONFIG_RT_GROUP_SCHED
 static int cpu_rt_runtime_write(struct cgroup_subsys_state *css,
@@ -9516,7 +9630,7 @@ static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_GROUP_SCHED_WEIGHT
 static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css,
 			       struct cftype *cft)
 {
@@ -9526,12 +9640,17 @@ 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
 
 static struct cftype cpu_legacy_files[] = {
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_GROUP_SCHED_WEIGHT
 	{
 		.name = "shares",
 		.read_u64 = cpu_shares_read_u64,
@@ -9641,38 +9760,35 @@ static int cpu_local_stat_show(struct seq_file *sf,
 	return 0;
 }
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_GROUP_SCHED_WEIGHT
+
 static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
 			       struct cftype *cft)
 {
-	struct task_group *tg = css_tg(css);
-	u64 weight = scale_load_down(tg->shares);
-
-	return DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024);
+	return sched_weight_to_cgroup(tg_weight(css_tg(css)));
 }
 
 static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
-				struct cftype *cft, u64 weight)
+				struct cftype *cft, u64 cgrp_weight)
 {
-	/*
-	 * cgroup weight knobs should use the common MIN, DFL and MAX
-	 * values which are 1, 100 and 10000 respectively.  While it loses
-	 * a bit of range on both ends, it maps pretty well onto the shares
-	 * value used by scheduler and the round-trip conversions preserve
-	 * the original value over the entire range.
-	 */
-	if (weight < CGROUP_WEIGHT_MIN || weight > CGROUP_WEIGHT_MAX)
+	unsigned long weight;
+	int ret;
+
+	if (cgrp_weight < CGROUP_WEIGHT_MIN || cgrp_weight > CGROUP_WEIGHT_MAX)
 		return -ERANGE;
 
-	weight = DIV_ROUND_CLOSEST_ULL(weight * 1024, CGROUP_WEIGHT_DFL);
+	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,
 				    struct cftype *cft)
 {
-	unsigned long weight = scale_load_down(css_tg(css)->shares);
+	unsigned long weight = tg_weight(css_tg(css));
 	int last_delta = INT_MAX;
 	int prio, delta;
 
@@ -9691,7 +9807,7 @@ 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;
@@ -9700,9 +9816,13 @@ 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
+#endif /* CONFIG_GROUP_SCHED_WEIGHT */
 
 static void __maybe_unused cpu_period_quota_print(struct seq_file *sf,
 						  long period, long quota)
@@ -9762,7 +9882,7 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of,
 #endif
 
 static struct cftype cpu_files[] = {
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_GROUP_SCHED_WEIGHT
 	{
 		.name = "weight",
 		.flags = CFTYPE_NOT_ON_ROOT,
@@ -9816,14 +9936,14 @@ 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,
@@ -10413,3 +10533,38 @@ void sched_mm_cid_fork(struct task_struct *t)
 	t->mm_cid_active = 1;
 }
 #endif
+
+#ifdef CONFIG_SCHED_CLASS_EXT
+void sched_deq_and_put_task(struct task_struct *p, int queue_flags,
+			    struct sched_enq_and_set_ctx *ctx)
+{
+	struct rq *rq = task_rq(p);
+
+	lockdep_assert_rq_held(rq);
+
+	*ctx = (struct sched_enq_and_set_ctx){
+		.p = p,
+		.queue_flags = queue_flags,
+		.queued = task_on_rq_queued(p),
+		.running = task_current(rq, p),
+	};
+
+	update_rq_clock(rq);
+	if (ctx->queued)
+		dequeue_task(rq, p, queue_flags | DEQUEUE_NOCLOCK);
+	if (ctx->running)
+		put_prev_task(rq, p);
+}
+
+void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx)
+{
+	struct rq *rq = task_rq(ctx->p);
+
+	lockdep_assert_rq_held(rq);
+
+	if (ctx->queued)
+		enqueue_task(rq, ctx->p, ctx->queue_flags | ENQUEUE_NOCLOCK);
+	if (ctx->running)
+		set_next_task(rq, ctx->p);
+}
+#endif	/* CONFIG_SCHED_CLASS_EXT */
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 43111a515a28..c6ba15388ea7 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -197,8 +197,10 @@ unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
 
 static void sugov_get_util(struct sugov_cpu *sg_cpu, unsigned long boost)
 {
-	unsigned long min, max, util = cpu_util_cfs_boost(sg_cpu->cpu);
+	unsigned long min, max, util = scx_cpuperf_target(sg_cpu->cpu);
 
+	if (!scx_switched_all())
+		util += cpu_util_cfs_boost(sg_cpu->cpu);
 	util = effective_cpu_util(sg_cpu->cpu, util, &min, &max);
 	util = max(util, boost);
 	sg_cpu->bw_min = min;
@@ -325,16 +327,35 @@ static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
-static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
+static bool sugov_hold_freq(struct sugov_cpu *sg_cpu)
 {
-	unsigned long idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu);
-	bool ret = idle_calls == sg_cpu->saved_idle_calls;
+	unsigned long idle_calls;
+	bool ret;
+
+	/*
+	 * The heuristics in this function is for the fair class. For SCX, the
+	 * performance target comes directly from the BPF scheduler. Let's just
+	 * follow it.
+	 */
+	if (scx_switched_all())
+		return false;
+
+	/* if capped by uclamp_max, always update to be in compliance */
+	if (uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)))
+		return false;
+
+	/*
+	 * Maintain the frequency if the CPU has not been idle recently, as
+	 * reduction is likely to be premature.
+	 */
+	idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu);
+	ret = idle_calls == sg_cpu->saved_idle_calls;
 
 	sg_cpu->saved_idle_calls = idle_calls;
 	return ret;
 }
 #else
-static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
+static inline bool sugov_hold_freq(struct sugov_cpu *sg_cpu) { return false; }
 #endif /* CONFIG_NO_HZ_COMMON */
 
 /*
@@ -382,14 +403,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
 		return;
 
 	next_f = get_next_freq(sg_policy, sg_cpu->util, max_cap);
-	/*
-	 * Do not reduce the frequency if the CPU has not been idle
-	 * recently, as the reduction is likely to be premature then.
-	 *
-	 * Except when the rq is capped by uclamp_max.
-	 */
-	if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
-	    sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
+
+	if (sugov_hold_freq(sg_cpu) && next_f < sg_policy->next_freq &&
 	    !sg_policy->need_freq_update) {
 		next_f = sg_policy->next_freq;
 
@@ -436,14 +451,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 	if (!sugov_update_single_common(sg_cpu, time, max_cap, flags))
 		return;
 
-	/*
-	 * Do not reduce the target performance level if the CPU has not been
-	 * idle recently, as the reduction is likely to be premature then.
-	 *
-	 * Except when the rq is capped by uclamp_max.
-	 */
-	if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
-	    sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
+	if (sugov_hold_freq(sg_cpu) && sg_cpu->util < prev_util)
 		sg_cpu->util = prev_util;
 
 	cpufreq_driver_adjust_perf(sg_cpu->cpu, sg_cpu->bw_min,
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index de1dc5264b3f..f4035c7a0fa1 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1264,6 +1264,9 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		P(dl.runtime);
 		P(dl.deadline);
 	}
+#ifdef CONFIG_SCHED_CLASS_EXT
+	__PS("ext.enabled", task_on_scx(p));
+#endif
 #undef PN_SCHEDSTAT
 #undef P_SCHEDSTAT
 
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
new file mode 100644
index 000000000000..9ee5a9a261cc
--- /dev/null
+++ b/kernel/sched/ext.c
@@ -0,0 +1,7173 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * BPF extensible scheduler