Merge branch 'main' into zstd-next

1 files changed, 311 insertions, 251 deletions

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index de53be905739..1644242ecd11 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2,86 +2,99 @@
 /*
  * Scheduler internal types and methods:
  */
-#include <linux/sched.h>
+#ifndef _KERNEL_SCHED_SCHED_H
+#define _KERNEL_SCHED_SCHED_H
 
+#include <linux/sched/affinity.h>
 #include <linux/sched/autogroup.h>
-#include <linux/sched/clock.h>
-#include <linux/sched/coredump.h>
 #include <linux/sched/cpufreq.h>
-#include <linux/sched/cputime.h>
 #include <linux/sched/deadline.h>
-#include <linux/sched/debug.h>
-#include <linux/sched/hotplug.h>
-#include <linux/sched/idle.h>
-#include <linux/sched/init.h>
-#include <linux/sched/isolation.h>
-#include <linux/sched/jobctl.h>
+#include <linux/sched.h>
 #include <linux/sched/loadavg.h>
 #include <linux/sched/mm.h>
-#include <linux/sched/nohz.h>
-#include <linux/sched/numa_balancing.h>
-#include <linux/sched/prio.h>
-#include <linux/sched/rt.h>
+#include <linux/sched/rseq_api.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/smt.h>
 #include <linux/sched/stat.h>
 #include <linux/sched/sysctl.h>
+#include <linux/sched/task_flags.h>
 #include <linux/sched/task.h>
-#include <linux/sched/task_stack.h>
 #include <linux/sched/topology.h>
-#include <linux/sched/user.h>
-#include <linux/sched/wake_q.h>
-#include <linux/sched/xacct.h>
-
-#include <uapi/linux/sched/types.h>
 
-#include <linux/binfmts.h>
-#include <linux/bitops.h>
-#include <linux/compat.h>
+#include <linux/atomic.h>
+#include <linux/bitmap.h>
+#include <linux/bug.h>
+#include <linux/capability.h>
+#include <linux/cgroup_api.h>
+#include <linux/cgroup.h>
 #include <linux/context_tracking.h>
 #include <linux/cpufreq.h>
-#include <linux/cpuidle.h>
-#include <linux/cpuset.h>
+#include <linux/cpumask_api.h>
 #include <linux/ctype.h>
-#include <linux/debugfs.h>
-#include <linux/delayacct.h>
-#include <linux/energy_model.h>
-#include <linux/init_task.h>
-#include <linux/kprobes.h>
+#include <linux/file.h>
+#include <linux/fs_api.h>
+#include <linux/hrtimer_api.h>
+#include <linux/interrupt.h>
+#include <linux/irq_work.h>
+#include <linux/jiffies.h>
+#include <linux/kref_api.h>
 #include <linux/kthread.h>
-#include <linux/membarrier.h>
-#include <linux/migrate.h>
-#include <linux/mmu_context.h>
-#include <linux/nmi.h>
+#include <linux/ktime_api.h>
+#include <linux/lockdep_api.h>
+#include <linux/lockdep.h>
+#include <linux/minmax.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/mutex_api.h>
+#include <linux/plist.h>
+#include <linux/poll.h>
 #include <linux/proc_fs.h>
-#include <linux/prefetch.h>
 #include <linux/profile.h>
 #include <linux/psi.h>
-#include <linux/ratelimit.h>
-#include <linux/rcupdate_wait.h>
-#include <linux/security.h>
+#include <linux/rcupdate.h>
+#include <linux/seq_file.h>
+#include <linux/seqlock.h>
+#include <linux/softirq.h>
+#include <linux/spinlock_api.h>
+#include <linux/static_key.h>
 #include <linux/stop_machine.h>
-#include <linux/suspend.h>
-#include <linux/swait.h>
+#include <linux/syscalls_api.h>
 #include <linux/syscalls.h>
-#include <linux/task_work.h>
-#include <linux/tsacct_kern.h>
+#include <linux/tick.h>
+#include <linux/topology.h>
+#include <linux/types.h>
+#include <linux/u64_stats_sync_api.h>
+#include <linux/uaccess.h>
+#include <linux/wait_api.h>
+#include <linux/wait_bit.h>
+#include <linux/workqueue_api.h>
+
+#include <trace/events/power.h>
+#include <trace/events/sched.h>
+
+#include "../workqueue_internal.h"
+
+#ifdef CONFIG_CGROUP_SCHED
+#include <linux/cgroup.h>
+#include <linux/psi.h>
+#endif
 
-#include <asm/tlb.h>
+#ifdef CONFIG_SCHED_DEBUG
+# include <linux/static_key.h>
+#endif
 
 #ifdef CONFIG_PARAVIRT
 # include <asm/paravirt.h>
+# include <asm/paravirt_api_clock.h>
 #endif
 
 #include "cpupri.h"
 #include "cpudeadline.h"
 
-#include <trace/events/sched.h>
-
 #ifdef CONFIG_SCHED_DEBUG
-# define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
+# define SCHED_WARN_ON(x)      WARN_ONCE(x, #x)
 #else
-# define SCHED_WARN_ON(x)	({ (void)(x), 0; })
+# define SCHED_WARN_ON(x)      ({ (void)(x), 0; })
 #endif
 
 struct rq;
@@ -96,10 +109,17 @@ extern __read_mostly int scheduler_running;
 extern unsigned long calc_load_update;
 extern atomic_long_t calc_load_tasks;
 
+extern unsigned int sysctl_sched_child_runs_first;
+
 extern void calc_global_load_tick(struct rq *this_rq);
 extern long calc_load_fold_active(struct rq *this_rq, long adjust);
 
 extern void call_trace_sched_update_nr_running(struct rq *rq, int count);
+
+extern unsigned int sysctl_sched_rt_period;
+extern int sysctl_sched_rt_runtime;
+extern int sched_rr_timeslice;
+
 /*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
@@ -301,44 +321,6 @@ struct dl_bw {
 	u64			total_bw;
 };
 
-static inline void __dl_update(struct dl_bw *dl_b, s64 bw);
-
-static inline
-void __dl_sub(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
-{
-	dl_b->total_bw -= tsk_bw;
-	__dl_update(dl_b, (s32)tsk_bw / cpus);
-}
-
-static inline
-void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
-{
-	dl_b->total_bw += tsk_bw;
-	__dl_update(dl_b, -((s32)tsk_bw / cpus));
-}
-
-static inline bool __dl_overflow(struct dl_bw *dl_b, unsigned long cap,
-				 u64 old_bw, u64 new_bw)
-{
-	return dl_b->bw != -1 &&
-	       cap_scale(dl_b->bw, cap) < dl_b->total_bw - old_bw + new_bw;
-}
-
-/*
- * Verify the fitness of task @p to run on @cpu taking into account the
- * CPU original capacity and the runtime/deadline ratio of the task.
- *
- * The function will return true if the CPU original capacity of the
- * @cpu scaled by SCHED_CAPACITY_SCALE >= runtime/deadline ratio of the
- * task and false otherwise.
- */
-static inline bool dl_task_fits_capacity(struct task_struct *p, int cpu)
-{
-	unsigned long cap = arch_scale_cpu_capacity(cpu);
-
-	return cap_scale(p->dl.dl_deadline, cap) >= p->dl.dl_runtime;
-}
-
 extern void init_dl_bw(struct dl_bw *dl_b);
 extern int  sched_dl_global_validate(void);
 extern void sched_dl_do_global(void);
@@ -347,15 +329,11 @@ extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr);
 extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr);
 extern bool __checkparam_dl(const struct sched_attr *attr);
 extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
-extern int  dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed);
 extern int  dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern bool dl_cpu_busy(unsigned int cpu);
+extern int  dl_cpu_busy(int cpu, struct task_struct *p);
 
 #ifdef CONFIG_CGROUP_SCHED
 
-#include <linux/cgroup.h>
-#include <linux/psi.h>
-
 struct cfs_rq;
 struct rt_rq;
 
@@ -488,9 +466,6 @@ extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
 extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
 extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
 
-extern void unregister_rt_sched_group(struct task_group *tg);
-extern void free_rt_sched_group(struct task_group *tg);
-extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent);
 extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 		struct sched_rt_entity *rt_se, int cpu,
 		struct sched_rt_entity *parent);
@@ -528,6 +503,49 @@ struct cfs_bandwidth { };
 
 #endif	/* CONFIG_CGROUP_SCHED */
 
+extern void unregister_rt_sched_group(struct task_group *tg);
+extern void free_rt_sched_group(struct task_group *tg);
+extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent);
+
+/*
+ * u64_u32_load/u64_u32_store
+ *
+ * Use a copy of a u64 value to protect against data race. This is only
+ * applicable for 32-bits architectures.
+ */
+#ifdef CONFIG_64BIT
+# define u64_u32_load_copy(var, copy)       var
+# define u64_u32_store_copy(var, copy, val) (var = val)
+#else
+# define u64_u32_load_copy(var, copy)					\
+({									\
+	u64 __val, __val_copy;						\
+	do {								\
+		__val_copy = copy;					\
+		/*							\
+		 * paired with u64_u32_store_copy(), ordering access	\
+		 * to var and copy.					\
+		 */							\
+		smp_rmb();						\
+		__val = var;						\
+	} while (__val != __val_copy);					\
+	__val;								\
+})
+# define u64_u32_store_copy(var, copy, val)				\
+do {									\
+	typeof(val) __val = (val);					\
+	var = __val;							\
+	/*								\
+	 * paired with u64_u32_load_copy(), ordering access to var and	\
+	 * copy.							\
+	 */								\
+	smp_wmb();							\
+	copy = __val;							\
+} while (0)
+#endif
+# define u64_u32_load(var)      u64_u32_load_copy(var, var##_copy)
+# define u64_u32_store(var, val) u64_u32_store_copy(var, var##_copy, val)
+
 /* CFS-related fields in a runqueue */
 struct cfs_rq {
 	struct load_weight	load;
@@ -568,7 +586,7 @@ struct cfs_rq {
 	 */
 	struct sched_avg	avg;
 #ifndef CONFIG_64BIT
-	u64			load_last_update_time_copy;
+	u64			last_update_time_copy;
 #endif
 	struct {
 		raw_spinlock_t	lock ____cacheline_aligned;
@@ -617,9 +635,13 @@ struct cfs_rq {
 	int			runtime_enabled;
 	s64			runtime_remaining;
 
+	u64			throttled_pelt_idle;
+#ifndef CONFIG_64BIT
+	u64                     throttled_pelt_idle_copy;
+#endif
 	u64			throttled_clock;
-	u64			throttled_clock_task;
-	u64			throttled_clock_task_time;
+	u64			throttled_clock_pelt;
+	u64			throttled_clock_pelt_time;
 	int			throttled;
 	int			throttle_count;
 	struct list_head	throttled_list;
@@ -989,6 +1011,12 @@ struct rq {
 	u64			clock_task ____cacheline_aligned;
 	u64			clock_pelt;
 	unsigned long		lost_idle_time;
+	u64			clock_pelt_idle;
+	u64			clock_idle;
+#ifndef CONFIG_64BIT
+	u64			clock_pelt_idle_copy;
+	u64			clock_idle_copy;
+#endif
 
 	atomic_t		nr_iowait;
 
@@ -1247,8 +1275,6 @@ static inline bool sched_group_cookie_match(struct rq *rq,
 	return false;
 }
 
-extern void queue_core_balance(struct rq *rq);
-
 static inline bool sched_core_enqueued(struct task_struct *p)
 {
 	return !RB_EMPTY_NODE(&p->core_node);
@@ -1282,10 +1308,6 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
 	return &rq->__lock;
 }
 
-static inline void queue_core_balance(struct rq *rq)
-{
-}
-
 static inline bool sched_cpu_cookie_match(struct rq *rq, struct task_struct *p)
 {
 	return true;
@@ -1662,12 +1684,14 @@ enum numa_topology_type {
 extern enum numa_topology_type sched_numa_topology_type;
 extern int sched_max_numa_distance;
 extern bool find_numa_distance(int distance);
-extern void sched_init_numa(void);
+extern void sched_init_numa(int offline_node);
+extern void sched_update_numa(int cpu, bool online);
 extern void sched_domains_numa_masks_set(unsigned int cpu);
 extern void sched_domains_numa_masks_clear(unsigned int cpu);
 extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu);
 #else
-static inline void sched_init_numa(void) { }
+static inline void sched_init_numa(int offline_node) { }
+static inline void sched_update_numa(int cpu, bool online) { }
 static inline void sched_domains_numa_masks_set(unsigned int cpu) { }
 static inline void sched_domains_numa_masks_clear(unsigned int cpu) { }
 static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
@@ -1705,6 +1729,11 @@ queue_balance_callback(struct rq *rq,
 {
 	lockdep_assert_rq_held(rq);
 
+	/*
+	 * Don't (re)queue an already queued item; nor queue anything when
+	 * balance_push() is active, see the comment with
+	 * balance_push_callback.
+	 */
 	if (unlikely(head->next || rq->balance_callback == &balance_push_callback))
 		return;
 
@@ -1771,6 +1800,11 @@ DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
 extern struct static_key_false sched_asym_cpucapacity;
 
+static __always_inline bool sched_asym_cpucap_active(void)
+{
+	return static_branch_unlikely(&sched_asym_cpucapacity);
+}
+
 struct sched_group_capacity {
 	atomic_t		ref;
 	/*
@@ -1822,15 +1856,6 @@ static inline struct cpumask *group_balance_mask(struct sched_group *sg)
 	return to_cpumask(sg->sgc->cpumask);
 }
 
-/**
- * group_first_cpu - Returns the first CPU in the cpumask of a sched_group.
- * @group: The group whose first CPU is to be returned.
- */
-static inline unsigned int group_first_cpu(struct sched_group *group)
-{
-	return cpumask_first(sched_group_span(group));
-}
-
 extern int group_balance_cpu(struct sched_group *sg);
 
 #ifdef CONFIG_SCHED_DEBUG
@@ -1846,15 +1871,9 @@ static inline void dirty_sched_domain_sysctl(int cpu)
 #endif
 
 extern int sched_update_scaling(void);
-
-extern void flush_smp_call_function_from_idle(void);
-
-#else /* !CONFIG_SMP: */
-static inline void flush_smp_call_function_from_idle(void) { }
-#endif
+#endif /* CONFIG_SMP */
 
 #include "stats.h"
-#include "autogroup.h"
 
 #if defined(CONFIG_SCHED_CORE) && defined(CONFIG_SCHEDSTATS)
 
@@ -1913,6 +1932,7 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 	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;
 #endif
 
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -1950,7 +1970,6 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
  * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
  */
 #ifdef CONFIG_SCHED_DEBUG
-# include <linux/static_key.h>
 # define const_debug __read_mostly
 #else
 # define const_debug const
@@ -2032,7 +2051,7 @@ static inline int task_current(struct rq *rq, struct task_struct *p)
 	return rq->curr == p;
 }
 
-static inline int task_running(struct rq *rq, struct task_struct *p)
+static inline int task_on_cpu(struct rq *rq, struct task_struct *p)
 {
 #ifdef CONFIG_SMP
 	return p->on_cpu;
@@ -2058,7 +2077,6 @@ static inline int task_on_rq_migrating(struct task_struct *p)
 
 #define WF_SYNC     0x10 /* Waker goes to sleep after wakeup */
 #define WF_MIGRATED 0x20 /* Internal use, task got migrated */
-#define WF_ON_CPU   0x40 /* Wakee is on_cpu */
 
 #ifdef CONFIG_SMP
 static_assert(WF_EXEC == SD_BALANCE_EXEC);
@@ -2177,11 +2195,8 @@ struct sched_class {
 
 	void (*update_curr)(struct rq *rq);
 
-#define TASK_SET_GROUP		0
-#define TASK_MOVE_GROUP		1
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	void (*task_change_group)(struct task_struct *p, int type);
+	void (*task_change_group)(struct task_struct *p);
 #endif
 };
 
@@ -2203,6 +2218,8 @@ static inline void set_next_task(struct rq *rq, struct task_struct *next)
  *
  *   include/asm-generic/vmlinux.lds.h
  *
+ * *CAREFUL* they are laid out in *REVERSE* order!!!
+ *
  * Also enforce alignment on the instance, not the type, to guarantee layout.
  */
 #define DEFINE_SCHED_CLASS(name) \
@@ -2211,17 +2228,16 @@ const struct sched_class name##_sched_class \
 	__section("__" #name "_sched_class")
 
 /* Defined in include/asm-generic/vmlinux.lds.h */
-extern struct sched_class __begin_sched_classes[];
-extern struct sched_class __end_sched_classes[];
-
-#define sched_class_highest (__end_sched_classes - 1)
-#define sched_class_lowest  (__begin_sched_classes - 1)
+extern struct sched_class __sched_class_highest[];
+extern struct sched_class __sched_class_lowest[];
 
 #define for_class_range(class, _from, _to) \
-	for (class = (_from); class != (_to); class--)
+	for (class = (_from); class < (_to); class++)
 
 #define for_each_class(class) \
-	for_class_range(class, sched_class_highest, sched_class_lowest)
+	for_class_range(class, __sched_class_highest, __sched_class_lowest)
+
+#define sched_class_above(_a, _b)	((_a) < (_b))
 
 extern const struct sched_class stop_sched_class;
 extern const struct sched_class dl_sched_class;
@@ -2330,8 +2346,8 @@ extern void resched_cpu(int cpu);
 
 extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
+extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
 
-extern struct dl_bandwidth def_dl_bandwidth;
 extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
 extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
 extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se);
@@ -2407,6 +2423,12 @@ extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
 
 extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 
+#ifdef CONFIG_PREEMPT_RT
+#define SCHED_NR_MIGRATE_BREAK 8
+#else
+#define SCHED_NR_MIGRATE_BREAK 32
+#endif
+
 extern const_debug unsigned int sysctl_sched_nr_migrate;
 extern const_debug unsigned int sysctl_sched_migration_cost;
 
@@ -2424,6 +2446,7 @@ extern unsigned int sysctl_numa_balancing_scan_delay;
 extern unsigned int sysctl_numa_balancing_scan_period_min;
 extern unsigned int sysctl_numa_balancing_scan_period_max;
 extern unsigned int sysctl_numa_balancing_scan_size;
+extern unsigned int sysctl_numa_balancing_hot_threshold;
 #endif
 
 #ifdef CONFIG_SCHED_HRTICK
@@ -2500,6 +2523,24 @@ unsigned long arch_scale_freq_capacity(int cpu)
 }
 #endif
 
+#ifdef CONFIG_SCHED_DEBUG
+/*
+ * In double_lock_balance()/double_rq_lock(), we use raw_spin_rq_lock() to
+ * acquire rq lock instead of rq_lock(). So at the end of these two functions
+ * we need to call double_rq_clock_clear_update() to clear RQCF_UPDATED of
+ * rq->clock_update_flags to avoid the WARN_DOUBLE_CLOCK warning.
+ */
+static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2)
+{
+	rq1->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
+	/* rq1 == rq2 for !CONFIG_SMP, so just clear RQCF_UPDATED once. */
+#ifdef CONFIG_SMP
+	rq2->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
+#endif
+}
+#else
+static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2) {}
+#endif
 
 #ifdef CONFIG_SMP
 
@@ -2565,14 +2606,15 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
 	__acquires(busiest->lock)
 	__acquires(this_rq->lock)
 {
-	if (__rq_lockp(this_rq) == __rq_lockp(busiest))
-		return 0;
-
-	if (likely(raw_spin_rq_trylock(busiest)))
+	if (__rq_lockp(this_rq) == __rq_lockp(busiest) ||
+	    likely(raw_spin_rq_trylock(busiest))) {
+		double_rq_clock_clear_update(this_rq, busiest);
 		return 0;
+	}
 
 	if (rq_order_less(this_rq, busiest)) {
 		raw_spin_rq_lock_nested(busiest, SINGLE_DEPTH_NESTING);
+		double_rq_clock_clear_update(this_rq, busiest);
 		return 0;
 	}
 
@@ -2662,10 +2704,11 @@ static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
 	__acquires(rq1->lock)
 	__acquires(rq2->lock)
 {
-	BUG_ON(!irqs_disabled());
-	BUG_ON(rq1 != rq2);
+	WARN_ON_ONCE(!irqs_disabled());
+	WARN_ON_ONCE(rq1 != rq2);
 	raw_spin_rq_lock(rq1);
 	__acquire(rq2->lock);	/* Fake it out ;) */
+	double_rq_clock_clear_update(rq1, rq2);
 }
 
 /*
@@ -2678,7 +2721,7 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 	__releases(rq1->lock)
 	__releases(rq2->lock)
 {
-	BUG_ON(rq1 != rq2);
+	WARN_ON_ONCE(rq1 != rq2);
 	raw_spin_rq_unlock(rq1);
 	__release(rq2->lock);
 }
@@ -2747,32 +2790,6 @@ extern void nohz_run_idle_balance(int cpu);
 static inline void nohz_run_idle_balance(int cpu) { }
 #endif
 
-#ifdef CONFIG_SMP
-static inline
-void __dl_update(struct dl_bw *dl_b, s64 bw)
-{
-	struct root_domain *rd = container_of(dl_b, struct root_domain, dl_bw);
-	int i;
-
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
-			 "sched RCU must be held");
-	for_each_cpu_and(i, rd->span, cpu_active_mask) {
-		struct rq *rq = cpu_rq(i);
-
-		rq->dl.extra_bw += bw;
-	}
-}
-#else
-static inline
-void __dl_update(struct dl_bw *dl_b, s64 bw)
-{
-	struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw);
-
-	dl->extra_bw += bw;
-}
-#endif
-
-
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 struct irqtime {
 	u64			total;
@@ -2841,88 +2858,6 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
 static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif /* CONFIG_CPU_FREQ */
 
-#ifdef CONFIG_UCLAMP_TASK
-unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
-
-/**
- * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values.
- * @rq:		The rq to clamp against. Must not be NULL.
- * @util:	The util value to clamp.
- * @p:		The task to clamp against. Can be NULL if you want to clamp
- *		against @rq only.
- *
- * Clamps the passed @util to the max(@rq, @p) effective uclamp values.
- *
- * If sched_uclamp_used static key is disabled, then just return the util
- * without any clamping since uclamp aggregation at the rq level in the fast
- * path is disabled, rendering this operation a NOP.
- *
- * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It
- * will return the correct effective uclamp value of the task even if the
- * static key is disabled.
- */
-static __always_inline
-unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
-				  struct task_struct *p)
-{
-	unsigned long min_util = 0;
-	unsigned long max_util = 0;
-
-	if (!static_branch_likely(&sched_uclamp_used))
-		return util;
-
-	if (p) {
-		min_util = uclamp_eff_value(p, UCLAMP_MIN);
-		max_util = uclamp_eff_value(p, UCLAMP_MAX);
-
-		/*
-		 * Ignore last runnable task's max clamp, as this task will
-		 * reset it. Similarly, no need to read the rq's min clamp.
-		 */
-		if (rq->uclamp_flags & UCLAMP_FLAG_IDLE)
-			goto out;
-	}
-
-	min_util = max_t(unsigned long, min_util, READ_ONCE(rq->uclamp[UCLAMP_MIN].value));
-	max_util = max_t(unsigned long, max_util, READ_ONCE(rq->uclamp[UCLAMP_MAX].value));
-out:
-	/*
-	 * Since CPU's {min,max}_util clamps are MAX aggregated considering
-	 * RUNNABLE tasks with _different_ clamps, we can end up with an
-	 * inversion. Fix it now when the clamps are applied.
-	 */
-	if (unlikely(min_util >= max_util))
-		return min_util;
-
-	return clamp(util, min_util, max_util);
-}
-
-/*
- * When uclamp is compiled in, the aggregation at rq level is 'turned off'
- * by default in the fast path and only gets turned on once userspace performs
- * an operation that requires it.
- *
- * Returns true if userspace opted-in to use uclamp and aggregation at rq level
- * hence is active.
- */
-static inline bool uclamp_is_used(void)
-{
-	return static_branch_likely(&sched_uclamp_used);
-}
-#else /* CONFIG_UCLAMP_TASK */
-static inline
-unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
-				  struct task_struct *p)
-{
-	return util;
-}
-
-static inline bool uclamp_is_used(void)
-{
-	return false;
-}
-#endif /* CONFIG_UCLAMP_TASK */
-
 #ifdef arch_scale_freq_capacity
 # ifndef arch_scale_freq_invariant
 #  define arch_scale_freq_invariant()	true
@@ -2953,9 +2888,24 @@ enum cpu_util_type {
 };
 
 unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
-				 unsigned long max, enum cpu_util_type type,
+				 enum cpu_util_type type,
 				 struct task_struct *p);
 
+/*
+ * Verify the fitness of task @p to run on @cpu taking into account the
+ * CPU original capacity and the runtime/deadline ratio of the task.
+ *
+ * The function will return true if the original capacity of @cpu is
+ * greater than or equal to task's deadline density right shifted by
+ * (BW_SHIFT - SCHED_CAPACITY_SHIFT) and false otherwise.
+ */
+static inline bool dl_task_fits_capacity(struct task_struct *p, int cpu)
+{
+	unsigned long cap = arch_scale_cpu_capacity(cpu);
+
+	return cap >= p->dl.dl_density >> (BW_SHIFT - SCHED_CAPACITY_SHIFT);
+}
+
 static inline unsigned long cpu_bw_dl(struct rq *rq)
 {
 	return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
@@ -3020,6 +2970,105 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
 }
 #endif
 
+#ifdef CONFIG_UCLAMP_TASK
+unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
+
+/**
+ * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values.
+ * @rq:		The rq to clamp against. Must not be NULL.
+ * @util:	The util value to clamp.
+ * @p:		The task to clamp against. Can be NULL if you want to clamp
+ *		against @rq only.
+ *
+ * Clamps the passed @util to the max(@rq, @p) effective uclamp values.
+ *
+ * If sched_uclamp_used static key is disabled, then just return the util
+ * without any clamping since uclamp aggregation at the rq level in the fast
+ * path is disabled, rendering this operation a NOP.
+ *
+ * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It
+ * will return the correct effective uclamp value of the task even if the
+ * static key is disabled.
+ */
+static __always_inline
+unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
+				  struct task_struct *p)
+{
+	unsigned long min_util = 0;
+	unsigned long max_util = 0;
+
+	if (!static_branch_likely(&sched_uclamp_used))
+		return util;
+
+	if (p) {
+		min_util = uclamp_eff_value(p, UCLAMP_MIN);
+		max_util = uclamp_eff_value(p, UCLAMP_MAX);
+
+		/*
+		 * Ignore last runnable task's max clamp, as this task will
+		 * reset it. Similarly, no need to read the rq's min clamp.
+		 */
+		if (rq->uclamp_flags & UCLAMP_FLAG_IDLE)
+			goto out;
+	}
+
+	min_util = max_t(unsigned long, min_util, READ_ONCE(rq->uclamp[UCLAMP_MIN].value));
+	max_util = max_t(unsigned long, max_util, READ_ONCE(rq->uclamp[UCLAMP_MAX].value));
+out:
+	/*
+	 * Since CPU's {min,max}_util clamps are MAX aggregated considering
+	 * RUNNABLE tasks with _different_ clamps, we can end up with an
+	 * inversion. Fix it now when the clamps are applied.
+	 */
+	if (unlikely(min_util >= max_util))
+		return min_util;
+
+	return clamp(util, min_util, max_util);
+}
+
+/* Is the rq being capped/throttled by uclamp_max? */
+static inline bool uclamp_rq_is_capped(struct rq *rq)
+{
+	unsigned long rq_util;
+	unsigned long max_util;
+
+	if (!static_branch_likely(&sched_uclamp_used))
+		return false;
+
+	rq_util = cpu_util_cfs(cpu_of(rq)) + cpu_util_rt(rq);
+	max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
+
+	return max_util != SCHED_CAPACITY_SCALE && rq_util >= max_util;
+}
+
+/*
+ * When uclamp is compiled in, the aggregation at rq level is 'turned off'
+ * by default in the fast path and only gets turned on once userspace performs
+ * an operation that requires it.
+ *
+ * Returns true if userspace opted-in to use uclamp and aggregation at rq level
+ * hence is active.
+ */
+static inline bool uclamp_is_used(void)
+{
+	return static_branch_likely(&sched_uclamp_used);
+}
+#else /* CONFIG_UCLAMP_TASK */
+static inline
+unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
+				  struct task_struct *p)
+{
+	return util;
+}
+
+static inline bool uclamp_rq_is_capped(struct rq *rq) { return false; }
+
+static inline bool uclamp_is_used(void)
+{
+	return false;
+}
+#endif /* CONFIG_UCLAMP_TASK */
+
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 static inline unsigned long cpu_util_irq(struct rq *rq)
 {
@@ -3118,3 +3167,14 @@ extern int sched_dynamic_mode(const char *str);
 extern void sched_dynamic_update(int mode);
 #endif
 
+static inline void update_current_exec_runtime(struct task_struct *curr,
+						u64 now, u64 delta_exec)
+{
+	curr->se.sum_exec_runtime += delta_exec;
+	account_group_exec_runtime(curr, delta_exec);
+
+	curr->se.exec_start = now;
+	cgroup_account_cputime(curr, delta_exec);
+}
+
+#endif /* _KERNEL_SCHED_SCHED_H */