Merge tag 'sched-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Core & fair scheduler changes:

   - Cancel the slice protection of the idle entity (Zihan Zhou)
   - Reduce the default slice to avoid tasks getting an extra tick
     (Zihan Zhou)
   - Force propagating min_slice of cfs_rq when {en,de}queue tasks
     (Tianchen Ding)
   - Refactor can_migrate_task() to elimate looping (I Hsin Cheng)
   - Add unlikey branch hints to several system calls (Colin Ian King)
   - Optimize current_clr_polling() on certain architectures (Yujun
     Dong)

  Deadline scheduler: (Juri Lelli)
   - Remove redundant dl_clear_root_domain call
   - Move dl_rebuild_rd_accounting to cpuset.h

  Uclamp:
   - Use the uclamp_is_used() helper instead of open-coding it (Xuewen
     Yan)
   - Optimize sched_uclamp_used static key enabling (Xuewen Yan)

  Scheduler topology support: (Juri Lelli)
   - Ignore special tasks when rebuilding domains
   - Add wrappers for sched_domains_mutex
   - Generalize unique visiting of root domains
   - Rebuild root domain accounting after every update
   - Remove partition_and_rebuild_sched_domains
   - Stop exposing partition_sched_domains_locked

  RSEQ: (Michael Jeanson)
   - Update kernel fields in lockstep with CONFIG_DEBUG_RSEQ=y
   - Fix segfault on registration when rseq_cs is non-zero
   - selftests: Add rseq syscall errors test
   - selftests: Ensure the rseq ABI TLS is actually 1024 bytes

  Membarriers:
   - Fix redundant load of membarrier_state (Nysal Jan K.A.)

  Scheduler debugging:
   - Introduce and use preempt_model_str() (Sebastian Andrzej Siewior)
   - Make CONFIG_SCHED_DEBUG unconditional (Ingo Molnar)

  Fixes and cleanups:
   - Always save/restore x86 TSC sched_clock() on suspend/resume
     (Guilherme G. Piccoli)
   - Misc fixes and cleanups (Thorsten Blum, Juri Lelli, Sebastian
     Andrzej Siewior)"

* tag 'sched-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  cpuidle, sched: Use smp_mb__after_atomic() in current_clr_polling()
  sched/debug: Remove CONFIG_SCHED_DEBUG
  sched/debug: Remove CONFIG_SCHED_DEBUG from self-test config files
  sched/debug, Documentation: Remove (most) CONFIG_SCHED_DEBUG references from documentation
  sched/debug: Make CONFIG_SCHED_DEBUG functionality unconditional
  sched/debug: Make 'const_debug' tunables unconditional __read_mostly
  sched/debug: Change SCHED_WARN_ON() to WARN_ON_ONCE()
  rseq/selftests: Fix namespace collision with rseq UAPI header
  include/{topology,cpuset}: Move dl_rebuild_rd_accounting to cpuset.h
  sched/topology: Stop exposing partition_sched_domains_locked
  cgroup/cpuset: Remove partition_and_rebuild_sched_domains
  sched/topology: Remove redundant dl_clear_root_domain call
  sched/deadline: Rebuild root domain accounting after every update
  sched/deadline: Generalize unique visiting of root domains
  sched/topology: Wrappers for sched_domains_mutex
  sched/deadline: Ignore special tasks when rebuilding domains
  tracing: Use preempt_model_str()
  xtensa: Rely on generic printing of preemption model
  x86: Rely on generic printing of preemption model
  s390: Rely on generic printing of preemption model
  ...

15 files changed, 363 insertions, 334 deletions

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 5a637292faa2..39c1fc643d77 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -953,10 +953,12 @@ static void dl_update_tasks_root_domain(struct cpuset *cs)
 	css_task_iter_end(&it);
 }
 
-static void dl_rebuild_rd_accounting(void)
+void dl_rebuild_rd_accounting(void)
 {
 	struct cpuset *cs = NULL;
 	struct cgroup_subsys_state *pos_css;
+	int cpu;
+	u64 cookie = ++dl_cookie;
 
 	lockdep_assert_held(&cpuset_mutex);
 	lockdep_assert_cpus_held();
@@ -964,11 +966,12 @@ static void dl_rebuild_rd_accounting(void)
 
 	rcu_read_lock();
 
-	/*
-	 * Clear default root domain DL accounting, it will be computed again
-	 * if a task belongs to it.
-	 */
-	dl_clear_root_domain(&def_root_domain);
+	for_each_possible_cpu(cpu) {
+		if (dl_bw_visited(cpu, cookie))
+			continue;
+
+		dl_clear_root_domain_cpu(cpu);
+	}
 
 	cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
 
@@ -989,16 +992,6 @@ static void dl_rebuild_rd_accounting(void)
 	rcu_read_unlock();
 }
 
-static void
-partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
-				    struct sched_domain_attr *dattr_new)
-{
-	mutex_lock(&sched_domains_mutex);
-	partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
-	dl_rebuild_rd_accounting();
-	mutex_unlock(&sched_domains_mutex);
-}
-
 /*
  * Rebuild scheduler domains.
  *
@@ -1060,7 +1053,7 @@ void rebuild_sched_domains_locked(void)
 	ndoms = generate_sched_domains(&doms, &attr);
 
 	/* Have scheduler rebuild the domains */
-	partition_and_rebuild_sched_domains(ndoms, doms, attr);
+	partition_sched_domains(ndoms, doms, attr);
 }
 #else /* !CONFIG_SMP */
 void rebuild_sched_domains_locked(void)
@@ -1082,6 +1075,13 @@ void rebuild_sched_domains(void)
 	cpus_read_unlock();
 }
 
+void cpuset_reset_sched_domains(void)
+{
+	mutex_lock(&cpuset_mutex);
+	partition_sched_domains(1, NULL, NULL);
+	mutex_unlock(&cpuset_mutex);
+}
+
 /**
  * cpuset_update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
  * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 2cb16091ec0a..b7a1ec327e81 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -78,24 +78,24 @@ efault:
 	return -EFAULT;
 }
 
-static void rseq_set_ro_fields(struct task_struct *t, u32 cpu_id_start, u32 cpu_id,
-			       u32 node_id, u32 mm_cid)
-{
-	rseq_kernel_fields(t)->cpu_id_start = cpu_id;
-	rseq_kernel_fields(t)->cpu_id = cpu_id;
-	rseq_kernel_fields(t)->node_id = node_id;
-	rseq_kernel_fields(t)->mm_cid = mm_cid;
-}
+/*
+ * Update an rseq field and its in-kernel copy in lock-step to keep a coherent
+ * state.
+ */
+#define rseq_unsafe_put_user(t, value, field, error_label)		\
+	do {								\
+		unsafe_put_user(value, &t->rseq->field, error_label);	\
+		rseq_kernel_fields(t)->field = value;			\
+	} while (0)
+
 #else
 static int rseq_validate_ro_fields(struct task_struct *t)
 {
 	return 0;
 }
 
-static void rseq_set_ro_fields(struct task_struct *t, u32 cpu_id_start, u32 cpu_id,
-			       u32 node_id, u32 mm_cid)
-{
-}
+#define rseq_unsafe_put_user(t, value, field, error_label)		\
+	unsafe_put_user(value, &t->rseq->field, error_label)
 #endif
 
 /*
@@ -173,17 +173,18 @@ static int rseq_update_cpu_node_id(struct task_struct *t)
 	WARN_ON_ONCE((int) mm_cid < 0);
 	if (!user_write_access_begin(rseq, t->rseq_len))
 		goto efault;
-	unsafe_put_user(cpu_id, &rseq->cpu_id_start, efault_end);
-	unsafe_put_user(cpu_id, &rseq->cpu_id, efault_end);
-	unsafe_put_user(node_id, &rseq->node_id, efault_end);
-	unsafe_put_user(mm_cid, &rseq->mm_cid, efault_end);
+
+	rseq_unsafe_put_user(t, cpu_id, cpu_id_start, efault_end);
+	rseq_unsafe_put_user(t, cpu_id, cpu_id, efault_end);
+	rseq_unsafe_put_user(t, node_id, node_id, efault_end);
+	rseq_unsafe_put_user(t, mm_cid, mm_cid, efault_end);
+
 	/*
 	 * Additional feature fields added after ORIG_RSEQ_SIZE
 	 * need to be conditionally updated only if
 	 * t->rseq_len != ORIG_RSEQ_SIZE.
 	 */
 	user_write_access_end();
-	rseq_set_ro_fields(t, cpu_id, cpu_id, node_id, mm_cid);
 	trace_rseq_update(t);
 	return 0;
 
@@ -195,6 +196,7 @@ efault:
 
 static int rseq_reset_rseq_cpu_node_id(struct task_struct *t)
 {
+	struct rseq __user *rseq = t->rseq;
 	u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED, node_id = 0,
 	    mm_cid = 0;
 
@@ -202,40 +204,61 @@ static int rseq_reset_rseq_cpu_node_id(struct task_struct *t)
 	 * Validate read-only rseq fields.
 	 */
 	if (rseq_validate_ro_fields(t))
-		return -EFAULT;
-	/*
-	 * Reset cpu_id_start to its initial state (0).
-	 */
-	if (put_user(cpu_id_start, &t->rseq->cpu_id_start))
-		return -EFAULT;
-	/*
-	 * Reset cpu_id to RSEQ_CPU_ID_UNINITIALIZED, so any user coming
-	 * in after unregistration can figure out that rseq needs to be
-	 * registered again.
-	 */
-	if (put_user(cpu_id, &t->rseq->cpu_id))
-		return -EFAULT;
-	/*
-	 * Reset node_id to its initial state (0).
-	 */
-	if (put_user(node_id, &t->rseq->node_id))
-		return -EFAULT;
+		goto efault;
+
+	if (!user_write_access_begin(rseq, t->rseq_len))
+		goto efault;
+
 	/*
-	 * Reset mm_cid to its initial state (0).
+	 * Reset all fields to their initial state.
+	 *
+	 * All fields have an initial state of 0 except cpu_id which is set to
+	 * RSEQ_CPU_ID_UNINITIALIZED, so that any user coming in after
+	 * unregistration can figure out that rseq needs to be registered
+	 * again.
 	 */
-	if (put_user(mm_cid, &t->rseq->mm_cid))
-		return -EFAULT;
-
-	rseq_set_ro_fields(t, cpu_id_start, cpu_id, node_id, mm_cid);
+	rseq_unsafe_put_user(t, cpu_id_start, cpu_id_start, efault_end);
+	rseq_unsafe_put_user(t, cpu_id, cpu_id, efault_end);
+	rseq_unsafe_put_user(t, node_id, node_id, efault_end);
+	rseq_unsafe_put_user(t, mm_cid, mm_cid, efault_end);
 
 	/*
 	 * Additional feature fields added after ORIG_RSEQ_SIZE
 	 * need to be conditionally reset only if
 	 * t->rseq_len != ORIG_RSEQ_SIZE.
 	 */
+	user_write_access_end();
+	return 0;
+
+efault_end:
+	user_write_access_end();
+efault:
+	return -EFAULT;
+}
+
+/*
+ * Get the user-space pointer value stored in the 'rseq_cs' field.
+ */
+static int rseq_get_rseq_cs_ptr_val(struct rseq __user *rseq, u64 *rseq_cs)
+{
+	if (!rseq_cs)
+		return -EFAULT;
+
+#ifdef CONFIG_64BIT
+	if (get_user(*rseq_cs, &rseq->rseq_cs))
+		return -EFAULT;
+#else
+	if (copy_from_user(rseq_cs, &rseq->rseq_cs, sizeof(*rseq_cs)))
+		return -EFAULT;
+#endif
+
 	return 0;
 }
 
+/*
+ * If the rseq_cs field of 'struct rseq' contains a valid pointer to
+ * user-space, copy 'struct rseq_cs' from user-space and validate its fields.
+ */
 static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 {
 	struct rseq_cs __user *urseq_cs;
@@ -244,17 +267,16 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 	u32 sig;
 	int ret;
 
-#ifdef CONFIG_64BIT
-	if (get_user(ptr, &t->rseq->rseq_cs))
-		return -EFAULT;
-#else
-	if (copy_from_user(&ptr, &t->rseq->rseq_cs, sizeof(ptr)))
-		return -EFAULT;
-#endif
+	ret = rseq_get_rseq_cs_ptr_val(t->rseq, &ptr);
+	if (ret)
+		return ret;
+
+	/* If the rseq_cs pointer is NULL, return a cleared struct rseq_cs. */
 	if (!ptr) {
 		memset(rseq_cs, 0, sizeof(*rseq_cs));
 		return 0;
 	}
+	/* Check that the pointer value fits in the user-space process space. */
 	if (ptr >= TASK_SIZE)
 		return -EINVAL;
 	urseq_cs = (struct rseq_cs __user *)(unsigned long)ptr;
@@ -330,7 +352,7 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
 	return !!event_mask;
 }
 
-static int clear_rseq_cs(struct task_struct *t)
+static int clear_rseq_cs(struct rseq __user *rseq)
 {
 	/*
 	 * The rseq_cs field is set to NULL on preemption or signal
@@ -341,9 +363,9 @@ static int clear_rseq_cs(struct task_struct *t)
 	 * Set rseq_cs to NULL.
 	 */
 #ifdef CONFIG_64BIT
-	return put_user(0UL, &t->rseq->rseq_cs);
+	return put_user(0UL, &rseq->rseq_cs);
 #else
-	if (clear_user(&t->rseq->rseq_cs, sizeof(t->rseq->rseq_cs)))
+	if (clear_user(&rseq->rseq_cs, sizeof(rseq->rseq_cs)))
 		return -EFAULT;
 	return 0;
 #endif
@@ -375,11 +397,11 @@ static int rseq_ip_fixup(struct pt_regs *regs)
 	 * Clear the rseq_cs pointer and return.
 	 */
 	if (!in_rseq_cs(ip, &rseq_cs))
-		return clear_rseq_cs(t);
+		return clear_rseq_cs(t->rseq);
 	ret = rseq_need_restart(t, rseq_cs.flags);
 	if (ret <= 0)
 		return ret;
-	ret = clear_rseq_cs(t);
+	ret = clear_rseq_cs(t->rseq);
 	if (ret)
 		return ret;
 	trace_rseq_ip_fixup(ip, rseq_cs.start_ip, rseq_cs.post_commit_offset,
@@ -453,6 +475,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 		int, flags, u32, sig)
 {
 	int ret;
+	u64 rseq_cs;
 
 	if (flags & RSEQ_FLAG_UNREGISTER) {
 		if (flags & ~RSEQ_FLAG_UNREGISTER)
@@ -507,6 +530,19 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 		return -EINVAL;
 	if (!access_ok(rseq, rseq_len))
 		return -EFAULT;
+
+	/*
+	 * If the rseq_cs pointer is non-NULL on registration, clear it to
+	 * avoid a potential segfault on return to user-space. The proper thing
+	 * to do would have been to fail the registration but this would break
+	 * older libcs that reuse the rseq area for new threads without
+	 * clearing the fields.
+	 */
+	if (rseq_get_rseq_cs_ptr_val(rseq, &rseq_cs))
+	        return -EFAULT;
+	if (rseq_cs && clear_rseq_cs(rseq))
+		return -EFAULT;
+
 #ifdef CONFIG_DEBUG_RSEQ
 	/*
 	 * Initialize the in-kernel rseq fields copy for validation of
diff --git a/kernel/sched/build_utility.c b/kernel/sched/build_utility.c
index 80a3df49ab47..bf9d8db94b70 100644
--- a/kernel/sched/build_utility.c
+++ b/kernel/sched/build_utility.c
@@ -68,9 +68,7 @@
 # include "cpufreq_schedutil.c"
 #endif
 
-#ifdef CONFIG_SCHED_DEBUG
-# include "debug.c"
-#endif
+#include "debug.c"
 
 #ifdef CONFIG_SCHEDSTATS
 # include "stats.c"
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fb313960f183..5bd8d7e7347d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -91,7 +91,6 @@
 #include "autogroup.h"
 #include "pelt.h"
 #include "smp.h"
-#include "stats.h"
 
 #include "../workqueue_internal.h"
 #include "../../io_uring/io-wq.h"
@@ -119,7 +118,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-#ifdef CONFIG_SCHED_DEBUG
 /*
  * Debugging: various feature bits
  *
@@ -129,7 +127,7 @@ DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
  */
 #define SCHED_FEAT(name, enabled)	\
 	(1UL << __SCHED_FEAT_##name) * enabled |
-const_debug unsigned int sysctl_sched_features =
+__read_mostly unsigned int sysctl_sched_features =
 #include "features.h"
 	0;
 #undef SCHED_FEAT
@@ -143,13 +141,12 @@ const_debug unsigned int sysctl_sched_features =
  */
 __read_mostly int sysctl_resched_latency_warn_ms = 100;
 __read_mostly int sysctl_resched_latency_warn_once = 1;
-#endif /* CONFIG_SCHED_DEBUG */
 
 /*
  * Number of tasks to iterate in a single balance run.
  * Limited because this is done with IRQs disabled.
  */
-const_debug unsigned int sysctl_sched_nr_migrate = SCHED_NR_MIGRATE_BREAK;
+__read_mostly unsigned int sysctl_sched_nr_migrate = SCHED_NR_MIGRATE_BREAK;
 
 __read_mostly int scheduler_running;
 
@@ -800,11 +797,10 @@ void update_rq_clock(struct rq *rq)
 	if (rq->clock_update_flags & RQCF_ACT_SKIP)
 		return;
 
-#ifdef CONFIG_SCHED_DEBUG
 	if (sched_feat(WARN_DOUBLE_CLOCK))
-		SCHED_WARN_ON(rq->clock_update_flags & RQCF_UPDATED);
+		WARN_ON_ONCE(rq->clock_update_flags & RQCF_UPDATED);
 	rq->clock_update_flags |= RQCF_UPDATED;
-#endif
+
 	clock = sched_clock_cpu(cpu_of(rq));
 	scx_rq_clock_update(rq, clock);
 
@@ -1720,7 +1716,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 
 	bucket = &uc_rq->bucket[uc_se->bucket_id];
 
-	SCHED_WARN_ON(!bucket->tasks);
+	WARN_ON_ONCE(!bucket->tasks);
 	if (likely(bucket->tasks))
 		bucket->tasks--;
 
@@ -1740,7 +1736,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 	 * Defensive programming: this should never happen. If it happens,
 	 * e.g. due to future modification, warn and fix up the expected value.
 	 */
-	SCHED_WARN_ON(bucket->value > rq_clamp);
+	WARN_ON_ONCE(bucket->value > rq_clamp);
 	if (bucket->value >= rq_clamp) {
 		bkt_clamp = uclamp_rq_max_value(rq, clamp_id, uc_se->value);
 		uclamp_rq_set(rq, clamp_id, bkt_clamp);
@@ -1757,7 +1753,7 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
 	 * The condition is constructed such that a NOP is generated when
 	 * sched_uclamp_used is disabled.
 	 */
-	if (!static_branch_unlikely(&sched_uclamp_used))
+	if (!uclamp_is_used())
 		return;
 
 	if (unlikely(!p->sched_class->uclamp_enabled))
@@ -1784,7 +1780,7 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 	 * The condition is constructed such that a NOP is generated when
 	 * sched_uclamp_used is disabled.
 	 */
-	if (!static_branch_unlikely(&sched_uclamp_used))
+	if (!uclamp_is_used())
 		return;
 
 	if (unlikely(!p->sched_class->uclamp_enabled))
@@ -1942,12 +1938,12 @@ static int sysctl_sched_uclamp_handler(const struct ctl_table *table, int write,
 	}
 
 	if (update_root_tg) {
-		static_branch_enable(&sched_uclamp_used);
+		sched_uclamp_enable();
 		uclamp_update_root_tg();
 	}
 
 	if (old_min_rt != sysctl_sched_uclamp_util_min_rt_default) {
-		static_branch_enable(&sched_uclamp_used);
+		sched_uclamp_enable();
 		uclamp_sync_util_min_rt_default();
 	}
 
@@ -2122,7 +2118,7 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
 
 void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	SCHED_WARN_ON(flags & DEQUEUE_SLEEP);
+	WARN_ON_ONCE(flags & DEQUEUE_SLEEP);
 
 	WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
 	ASSERT_EXCLUSIVE_WRITER(p->on_rq);
@@ -2727,7 +2723,7 @@ __do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
 	 * XXX do further audits, this smells like something putrid.
 	 */
 	if (ctx->flags & SCA_MIGRATE_DISABLE)
-		SCHED_WARN_ON(!p->on_cpu);
+		WARN_ON_ONCE(!p->on_cpu);
 	else
 		lockdep_assert_held(&p->pi_lock);
 
@@ -3292,7 +3288,6 @@ void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
 
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
-#ifdef CONFIG_SCHED_DEBUG
 	unsigned int state = READ_ONCE(p->__state);
 
 	/*
@@ -3330,7 +3325,6 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	WARN_ON_ONCE(!cpu_online(new_cpu));
 
 	WARN_ON_ONCE(is_migration_disabled(p));
-#endif
 
 	trace_sched_migrate_task(p, new_cpu);
 
@@ -4191,7 +4185,7 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		 *  - we're serialized against set_special_state() by virtue of
 		 *    it disabling IRQs (this allows not taking ->pi_lock).
 		 */
-		SCHED_WARN_ON(p->se.sched_delayed);
+		WARN_ON_ONCE(p->se.sched_delayed);
 		if (!ttwu_state_match(p, state, &success))
 			goto out;
 
@@ -4485,7 +4479,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	INIT_LIST_HEAD(&p->se.group_node);
 
 	/* A delayed task cannot be in clone(). */
-	SCHED_WARN_ON(p->se.sched_delayed);
+	WARN_ON_ONCE(p->se.sched_delayed);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	p->se.cfs_rq			= NULL;
@@ -5573,7 +5567,6 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 	return ns;
 }
 
-#ifdef CONFIG_SCHED_DEBUG
 static u64 cpu_resched_latency(struct rq *rq)
 {
 	int latency_warn_ms = READ_ONCE(sysctl_resched_latency_warn_ms);
@@ -5618,9 +5611,6 @@ static int __init setup_resched_latency_warn_ms(char *str)
 	return 1;
 }
 __setup("resched_latency_warn_ms=", setup_resched_latency_warn_ms);
-#else
-static inline u64 cpu_resched_latency(struct rq *rq) { return 0; }
-#endif /* CONFIG_SCHED_DEBUG */
 
 /*
  * This function gets called by the timer code, with HZ frequency.
@@ -5741,7 +5731,7 @@ static void sched_tick_remote(struct work_struct *work)
 			 * we are always sure that there is no proxy (only a
 			 * single task is running).
 			 */
-			SCHED_WARN_ON(rq->curr != rq->donor);
+			WARN_ON_ONCE(rq->curr != rq->donor);
 			update_rq_clock(rq);
 
 			if (!is_idle_task(curr)) {
@@ -5961,7 +5951,7 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt)
 		preempt_count_set(PREEMPT_DISABLED);
 	}
 	rcu_sleep_check();
-	SCHED_WARN_ON(ct_state() == CT_STATE_USER);
+	WARN_ON_ONCE(ct_state() == CT_STATE_USER);
 
 	profile_hit(SCHED_PROFILING, __builtin_return_address(0));
 
@@ -6714,9 +6704,7 @@ static void __sched notrace __schedule(int sched_mode)
 picked:
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
-#ifdef CONFIG_SCHED_DEBUG
 	rq->last_seen_need_resched_ns = 0;
-#endif
 
 	if (likely(prev != next)) {
 		rq->nr_switches++;
@@ -6807,7 +6795,7 @@ static inline void sched_submit_work(struct task_struct *tsk)
 	 * deadlock if the callback attempts to acquire a lock which is
 	 * already acquired.
 	 */
-	SCHED_WARN_ON(current->__state & TASK_RTLOCK_WAIT);
+	WARN_ON_ONCE(current->__state & TASK_RTLOCK_WAIT);
 
 	/*
 	 * If we are going to sleep and we have plugged IO queued,
@@ -7090,7 +7078,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
 int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
 			  void *key)
 {
-	WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~(WF_SYNC|WF_CURRENT_CPU));
+	WARN_ON_ONCE(wake_flags & ~(WF_SYNC|WF_CURRENT_CPU));
 	return try_to_wake_up(curr->private, mode, wake_flags);
 }
 EXPORT_SYMBOL(default_wake_function);
@@ -7644,10 +7632,57 @@ PREEMPT_MODEL_ACCESSOR(lazy);
 
 #else /* !CONFIG_PREEMPT_DYNAMIC: */
 
+#define preempt_dynamic_mode -1
+
 static inline void preempt_dynamic_init(void) { }
 
 #endif /* CONFIG_PREEMPT_DYNAMIC */
 
+const char *preempt_modes[] = {
+	"none", "voluntary", "full", "lazy", NULL,
+};
+
+const char *preempt_model_str(void)
+{
+	bool brace = IS_ENABLED(CONFIG_PREEMPT_RT) &&
+		(IS_ENABLED(CONFIG_PREEMPT_DYNAMIC) ||
+		 IS_ENABLED(CONFIG_PREEMPT_LAZY));
+	static char buf[128];
+
+	if (IS_ENABLED(CONFIG_PREEMPT_BUILD)) {
+		struct seq_buf s;
+
+		seq_buf_init(&s, buf, sizeof(buf));
+		seq_buf_puts(&s, "PREEMPT");
+
+		if (IS_ENABLED(CONFIG_PREEMPT_RT))
+			seq_buf_printf(&s, "%sRT%s",
+				       brace ? "_{" : "_",
+				       brace ? "," : "");
+
+		if (IS_ENABLED(CONFIG_PREEMPT_DYNAMIC)) {
+			seq_buf_printf(&s, "(%s)%s",
+				       preempt_dynamic_mode > 0 ?
+				       preempt_modes[preempt_dynamic_mode] : "undef",
+				       brace ? "}" : "");
+			return seq_buf_str(&s);
+		}
+
+		if (IS_ENABLED(CONFIG_PREEMPT_LAZY)) {
+			seq_buf_printf(&s, "LAZY%s",
+				       brace ? "}" : "");
+			return seq_buf_str(&s);
+		}
+
+		return seq_buf_str(&s);
+	}
+
+	if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY_BUILD))
+		return "VOLUNTARY";
+
+	return "NONE";
+}
+
 int io_schedule_prepare(void)
 {
 	int old_iowait = current->in_iowait;
@@ -7762,10 +7797,9 @@ void show_state_filter(unsigned int state_filter)
 			sched_show_task(p);
 	}
 
-#ifdef CONFIG_SCHED_DEBUG
 	if (!state_filter)
 		sysrq_sched_debug_show();
-#endif
+
 	rcu_read_unlock();
 	/*
 	 * Only show locks if all tasks are dumped:
@@ -8180,7 +8214,7 @@ static void cpuset_cpu_active(void)
 		 * operation in the resume sequence, just build a single sched
 		 * domain, ignoring cpusets.
 		 */
-		partition_sched_domains(1, NULL, NULL);
+		cpuset_reset_sched_domains();
 		if (--num_cpus_frozen)
 			return;
 		/*
@@ -8199,7 +8233,7 @@ static void cpuset_cpu_inactive(unsigned int cpu)
 		cpuset_update_active_cpus();
 	} else {
 		num_cpus_frozen++;
-		partition_sched_domains(1, NULL, NULL);
+		cpuset_reset_sched_domains();
 	}
 }
 
@@ -8421,9 +8455,9 @@ void __init sched_init_smp(void)
 	 * CPU masks are stable and all blatant races in the below code cannot
 	 * happen.
 	 */
-	mutex_lock(&sched_domains_mutex);
+	sched_domains_mutex_lock();
 	sched_init_domains(cpu_active_mask);
-	mutex_unlock(&sched_domains_mutex);
+	sched_domains_mutex_unlock();
 
 	/* Move init over to a non-isolated CPU */
 	if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_DOMAIN)) < 0)
@@ -9185,7 +9219,7 @@ static void cpu_util_update_eff(struct cgroup_subsys_state *css)
 	unsigned int clamps;
 
 	lockdep_assert_held(&uclamp_mutex);
-	SCHED_WARN_ON(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	css_for_each_descendant_pre(css, top_css) {
 		uc_parent = css_tg(css)->parent
@@ -9277,7 +9311,7 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
 	if (req.ret)
 		return req.ret;
 
-	static_branch_enable(&sched_uclamp_used);
+	sched_uclamp_enable();
 
 	guard(mutex)(&uclamp_mutex);
 	guard(rcu)();
@@ -10520,7 +10554,7 @@ static void task_mm_cid_work(struct callback_head *work)
 	struct mm_struct *mm;
 	int weight, cpu;
 
-	SCHED_WARN_ON(t != container_of(work, struct task_struct, cid_work));
+	WARN_ON_ONCE(t != container_of(work, struct task_struct, cid_work));
 
 	work->next = work;	/* Prevent double-add */
 	if (t->flags & PF_EXITING)
diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c
index 1ef98a93eb1d..c4606ca89210 100644
--- a/kernel/sched/core_sched.c
+++ b/kernel/sched/core_sched.c
@@ -65,7 +65,7 @@ static unsigned long sched_core_update_cookie(struct task_struct *p,
 	 * a cookie until after we've removed it, we must have core scheduling
 	 * enabled here.
 	 */
-	SCHED_WARN_ON((p->core_cookie || cookie) && !sched_core_enabled(rq));
+	WARN_ON_ONCE((p->core_cookie || cookie) && !sched_core_enabled(rq));
 
 	if (sched_core_enqueued(p))
 		sched_core_dequeue(rq, p, DEQUEUE_SAVE);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index ff4df16b5186..03a33b597768 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -166,14 +166,14 @@ static inline unsigned long dl_bw_capacity(int i)
 	}
 }
 
-static inline bool dl_bw_visited(int cpu, u64 gen)
+bool dl_bw_visited(int cpu, u64 cookie)
 {
 	struct root_domain *rd = cpu_rq(cpu)->rd;
 
-	if (rd->visit_gen == gen)
+	if (rd->visit_cookie == cookie)
 		return true;
 
-	rd->visit_gen = gen;
+	rd->visit_cookie = cookie;
 	return false;
 }
 
@@ -207,7 +207,7 @@ static inline unsigned long dl_bw_capacity(int i)
 	return SCHED_CAPACITY_SCALE;
 }
 
-static inline bool dl_bw_visited(int cpu, u64 gen)
+bool dl_bw_visited(int cpu, u64 cookie)
 {
 	return false;
 }
@@ -249,8 +249,8 @@ void __add_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
 
 	lockdep_assert_rq_held(rq_of_dl_rq(dl_rq));
 	dl_rq->running_bw += dl_bw;
-	SCHED_WARN_ON(dl_rq->running_bw < old); /* overflow */
-	SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw);
+	WARN_ON_ONCE(dl_rq->running_bw < old); /* overflow */
+	WARN_ON_ONCE(dl_rq->running_bw > dl_rq->this_bw);
 	/* kick cpufreq (see the comment in kernel/sched/sched.h). */
 	cpufreq_update_util(rq_of_dl_rq(dl_rq), 0);
 }
@@ -262,7 +262,7 @@ void __sub_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
 
 	lockdep_assert_rq_held(rq_of_dl_rq(dl_rq));
 	dl_rq->running_bw -= dl_bw;
-	SCHED_WARN_ON(dl_rq->running_bw > old); /* underflow */
+	WARN_ON_ONCE(dl_rq->running_bw > old); /* underflow */
 	if (dl_rq->running_bw > old)
 		dl_rq->running_bw = 0;
 	/* kick cpufreq (see the comment in kernel/sched/sched.h). */
@@ -276,7 +276,7 @@ void __add_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
 
 	lockdep_assert_rq_held(rq_of_dl_rq(dl_rq));
 	dl_rq->this_bw += dl_bw;
-	SCHED_WARN_ON(dl_rq->this_bw < old); /* overflow */
+	WARN_ON_ONCE(dl_rq->this_bw < old); /* overflow */
 }
 
 static inline
@@ -286,10 +286,10 @@ void __sub_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
 
 	lockdep_assert_rq_held(rq_of_dl_rq(dl_rq));
 	dl_rq->this_bw -= dl_bw;
-	SCHED_WARN_ON(dl_rq->this_bw > old); /* underflow */
+	WARN_ON_ONCE(dl_rq->this_bw > old); /* underflow */
 	if (dl_rq->this_bw > old)
 		dl_rq->this_bw = 0;
-	SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw);
+	WARN_ON_ONCE(dl_rq->running_bw > dl_rq->this_bw);
 }
 
 static inline
@@ -2956,7 +2956,7 @@ void dl_add_task_root_domain(struct task_struct *p)
 	struct dl_bw *dl_b;
 
 	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
-	if (!dl_task(p)) {
+	if (!dl_task(p) || dl_entity_is_special(&p->dl)) {
 		raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
 		return;
 	}
@@ -2981,18 +2981,22 @@ void dl_clear_root_domain(struct root_domain *rd)
 	rd->dl_bw.total_bw = 0;
 
 	/*
-	 * dl_server bandwidth is only restored when CPUs are attached to root
-	 * domains (after domains are created or CPUs moved back to the
-	 * default root doamin).
+	 * dl_servers are not tasks. Since dl_add_task_root_domain ignores
+	 * them, we need to account for them here explicitly.
 	 */
 	for_each_cpu(i, rd->span) {
 		struct sched_dl_entity *dl_se = &cpu_rq(i)->fair_server;
 
 		if (dl_server(dl_se) && cpu_active(i))
-			rd->dl_bw.total_bw += dl_se->dl_bw;
+			__dl_add(&rd->dl_bw, dl_se->dl_bw, dl_bw_cpus(i));
 	}
 }
 
+void dl_clear_root_domain_cpu(int cpu)
+{
+	dl_clear_root_domain(cpu_rq(cpu)->rd);
+}
+
 #endif /* CONFIG_SMP */
 
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
@@ -3171,15 +3175,18 @@ DEFINE_SCHED_CLASS(dl) = {
 #endif
 };
 
-/* Used for dl_bw check and update, used under sched_rt_handler()::mutex */
-static u64 dl_generation;
+/*
+ * Used for dl_bw check and update, used under sched_rt_handler()::mutex and
+ * sched_domains_mutex.
+ */
+u64 dl_cookie;
 
 int sched_dl_global_validate(void)
 {
 	u64 runtime = global_rt_runtime();
 	u64 period = global_rt_period();
 	u64 new_bw = to_ratio(period, runtime);
-	u64 gen = ++dl_generation;
+	u64 cookie = ++dl_cookie;
 	struct dl_bw *dl_b;
 	int cpu, cpus, ret = 0;
 	unsigned long flags;
@@ -3192,7 +3199,7 @@ int sched_dl_global_validate(void)
 	for_each_online_cpu(cpu) {
 		rcu_read_lock_sched();
 
-		if (dl_bw_visited(cpu, gen))
+		if (dl_bw_visited(cpu, cookie))
 			goto next;
 
 		dl_b = dl_bw_of(cpu);
@@ -3229,7 +3236,7 @@ static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
 void sched_dl_do_global(void)
 {
 	u64 new_bw = -1;
-	u64 gen = ++dl_generation;
+	u64 cookie = ++dl_cookie;
 	struct dl_bw *dl_b;
 	int cpu;
 	unsigned long flags;
@@ -3240,7 +3247,7 @@ void sched_dl_do_global(void)
 	for_each_possible_cpu(cpu) {
 		rcu_read_lock_sched();
 
-		if (dl_bw_visited(cpu, gen)) {
+		if (dl_bw_visited(cpu, cookie)) {
 			rcu_read_unlock_sched();
 			continue;
 		}
@@ -3567,9 +3574,7 @@ void dl_bw_free(int cpu, u64 dl_bw)
 }
 #endif
 
-#ifdef CONFIG_SCHED_DEBUG
 void print_dl_stats(struct seq_file *m, int cpu)
 {
 	print_dl_rq(m, cpu, &cpu_rq(cpu)->dl);
 }
-#endif /* CONFIG_SCHED_DEBUG */
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index ef047add7f9e..56ae54e0ce6a 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -244,11 +244,13 @@ static ssize_t sched_dynamic_write(struct file *filp, const char __user *ubuf,
 
 static int sched_dynamic_show(struct seq_file *m, void *v)
 {
-	static const char * preempt_modes[] = {
-		"none", "voluntary", "full", "lazy",
-	};
-	int j = ARRAY_SIZE(preempt_modes) - !IS_ENABLED(CONFIG_ARCH_HAS_PREEMPT_LAZY);
 	int i = IS_ENABLED(CONFIG_PREEMPT_RT) * 2;
+	int j;
+
+	/* Count entries in NULL terminated preempt_modes */
+	for (j = 0; preempt_modes[j]; j++)
+		;
+	j -= !IS_ENABLED(CONFIG_ARCH_HAS_PREEMPT_LAZY);
 
 	for (; i < j; i++) {
 		if (preempt_dynamic_mode == i)
@@ -292,7 +294,7 @@ static ssize_t sched_verbose_write(struct file *filp, const char __user *ubuf,
 	bool orig;
 
 	cpus_read_lock();
-	mutex_lock(&sched_domains_mutex);
+	sched_domains_mutex_lock();
 
 	orig = sched_debug_verbose;
 	result = debugfs_write_file_bool(filp, ubuf, cnt, ppos);
@@ -304,7 +306,7 @@ static ssize_t sched_verbose_write(struct file *filp, const char __user *ubuf,
 		sd_dentry = NULL;
 	}
 
-	mutex_unlock(&sched_domains_mutex);
+	sched_domains_mutex_unlock();
 	cpus_read_unlock();
 
 	return result;
@@ -515,9 +517,9 @@ static __init int sched_init_debug(void)
 	debugfs_create_u32("migration_cost_ns", 0644, debugfs_sched, &sysctl_sched_migration_cost);
 	debugfs_create_u32("nr_migrate", 0644, debugfs_sched, &sysctl_sched_nr_migrate);
 
-	mutex_lock(&sched_domains_mutex);
+	sched_domains_mutex_lock();
 	update_sched_domain_debugfs();
-	mutex_unlock(&sched_domains_mutex);
+	sched_domains_mutex_unlock();
 #endif
 
 #ifdef CONFIG_NUMA_BALANCING
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 06561d6717c9..21575d39c376 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2472,7 +2472,7 @@ static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq,
 {
 	int cpu = cpu_of(rq);
 
-	SCHED_WARN_ON(task_cpu(p) == cpu);
+	WARN_ON_ONCE(task_cpu(p) == cpu);
 
 	/*
 	 * If @p has migration disabled, @p->cpus_ptr is updated to contain only
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c798d2795243..a0c4cd26ee07 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -74,12 +74,12 @@ unsigned int sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_LOG;
 /*
  * Minimal preemption granularity for CPU-bound tasks:
  *
- * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 0.70 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_base_slice			= 750000ULL;
-static unsigned int normalized_sysctl_sched_base_slice	= 750000ULL;
+unsigned int sysctl_sched_base_slice			= 700000ULL;
+static unsigned int normalized_sysctl_sched_base_slice	= 700000ULL;
 
-const_debug unsigned int sysctl_sched_migration_cost	= 500000UL;
+__read_mostly unsigned int sysctl_sched_migration_cost	= 500000UL;
 
 static int __init setup_sched_thermal_decay_shift(char *str)
 {
@@ -399,7 +399,7 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 
 static inline void assert_list_leaf_cfs_rq(struct rq *rq)
 {
-	SCHED_WARN_ON(rq->tmp_alone_branch != &rq->leaf_cfs_rq_list);
+	WARN_ON_ONCE(rq->tmp_alone_branch != &rq->leaf_cfs_rq_list);
 }
 
 /* Iterate through all leaf cfs_rq's on a runqueue */
@@ -696,7 +696,7 @@ static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	s64 vlag, limit;
 
-	SCHED_WARN_ON(!se->on_rq);
+	WARN_ON_ONCE(!se->on_rq);
 
 	vlag = avg_vruntime(cfs_rq) - se->vruntime;
 	limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
@@ -884,6 +884,26 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
 }
 
 /*
+ * HACK, stash a copy of deadline at the point of pick in vlag,
+ * which isn't used until dequeue.
+ */
+static inline void set_protect_slice(struct sched_entity *se)
+{
+	se->vlag = se->deadline;
+}
+
+static inline bool protect_slice(struct sched_entity *se)
+{
+	return se->vlag == se->deadline;
+}
+
+static inline void cancel_protect_slice(struct sched_entity *se)
+{
+	if (protect_slice(se))
+		se->vlag = se->deadline + 1;
+}
+
+/*
  * Earliest Eligible Virtual Deadline First
  *
  * In order to provide latency guarantees for different request sizes
@@ -919,11 +939,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
 	if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
 		curr = NULL;
 
-	/*
-	 * Once selected, run a task until it either becomes non-eligible or
-	 * until it gets a new slice. See the HACK in set_next_entity().
-	 */
-	if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline)
+	if (sched_feat(RUN_TO_PARITY) && curr && protect_slice(curr))
 		return curr;
 
 	/* Pick the leftmost entity if it's eligible */
@@ -967,7 +983,6 @@ found:
 	return best;
 }
 
-#ifdef CONFIG_SCHED_DEBUG
 struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *last = rb_last(&cfs_rq->tasks_timeline.rb_root);
@@ -994,7 +1009,6 @@ int sched_update_scaling(void)
 	return 0;
 }
 #endif
-#endif
 
 static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se);
 
@@ -3301,7 +3315,7 @@ static void task_numa_work(struct callback_head *work)
 	bool vma_pids_skipped;
 	bool vma_pids_forced = false;
 
-	SCHED_WARN_ON(p != container_of(work, struct task_struct, numa_work));
+	WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));
 
 	work->next = work;
 	/*
@@ -4020,7 +4034,7 @@ static inline bool load_avg_is_decayed(struct sched_avg *sa)
 	 * Make sure that rounding and/or propagation of PELT values never
 	 * break this.
 	 */
-	SCHED_WARN_ON(sa->load_avg ||
+	WARN_ON_ONCE(sa->load_avg ||
 		      sa->util_avg ||
 		      sa->runnable_avg);
 
@@ -5444,7 +5458,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	clear_buddies(cfs_rq, se);
 
 	if (flags & DEQUEUE_DELAYED) {
-		SCHED_WARN_ON(!se->sched_delayed);
+		WARN_ON_ONCE(!se->sched_delayed);
 	} else {
 		bool delay = sleep;
 		/*
@@ -5454,7 +5468,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		if (flags & DEQUEUE_SPECIAL)
 			delay = false;
 
-		SCHED_WARN_ON(delay && se->sched_delayed);
+		WARN_ON_ONCE(delay && se->sched_delayed);
 
 		if (sched_feat(DELAY_DEQUEUE) && delay &&
 		    !entity_eligible(cfs_rq, se)) {
@@ -5530,15 +5544,12 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		update_stats_wait_end_fair(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
 		update_load_avg(cfs_rq, se, UPDATE_TG);
-		/*
-		 * HACK, stash a copy of deadline at the point of pick in vlag,
-		 * which isn't used until dequeue.
-		 */
-		se->vlag = se->deadline;
+
+		set_protect_slice(se);
 	}
 
 	update_stats_curr_start(cfs_rq, se);
-	SCHED_WARN_ON(cfs_rq->curr);
+	WARN_ON_ONCE(cfs_rq->curr);
 	cfs_rq->curr = se;
 
 	/*
@@ -5579,7 +5590,7 @@ pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq)
 	if (sched_feat(PICK_BUDDY) &&
 	    cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next)) {
 		/* ->next will never be delayed */
-		SCHED_WARN_ON(cfs_rq->next->sched_delayed);
+		WARN_ON_ONCE(cfs_rq->next->sched_delayed);
 		return cfs_rq->next;
 	}
 
@@ -5615,7 +5626,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 		/* in !on_rq case, update occurred at dequeue */
 		update_load_avg(cfs_rq, prev, 0);
 	}
-	SCHED_WARN_ON(cfs_rq->curr != prev);
+	WARN_ON_ONCE(cfs_rq->curr != prev);
 	cfs_rq->curr = NULL;
 }
 
@@ -5838,7 +5849,7 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
 
 			cfs_rq->throttled_clock_self = 0;
 
-			if (SCHED_WARN_ON((s64)delta < 0))
+			if (WARN_ON_ONCE((s64)delta < 0))
 				delta = 0;
 
 			cfs_rq->throttled_clock_self_time += delta;
@@ -5858,7 +5869,7 @@ static int tg_throttle_down(struct task_group *tg, void *data)
 		cfs_rq->throttled_clock_pelt = rq_clock_pelt(rq);
 		list_del_leaf_cfs_rq(cfs_rq);
 
-		SCHED_WARN_ON(cfs_rq->throttled_clock_self);
+		WARN_ON_ONCE(cfs_rq->throttled_clock_self);
 		if (cfs_rq->nr_queued)
 			cfs_rq->throttled_clock_self = rq_clock(rq);
 	}
@@ -5967,7 +5978,7 @@ done:
 	 * throttled-list.  rq->lock protects completion.
 	 */
 	cfs_rq->throttled = 1;
-	SCHED_WARN_ON(cfs_rq->throttled_clock);
+	WARN_ON_ONCE(cfs_rq->throttled_clock);
 	if (cfs_rq->nr_queued)
 		cfs_rq->throttled_clock = rq_clock(rq);
 	return true;
@@ -6123,7 +6134,7 @@ static inline void __unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq)
 	}
 
 	/* Already enqueued */
-	if (SCHED_WARN_ON(!list_empty(&cfs_rq->throttled_csd_list)))
+	if (WARN_ON_ONCE(!list_empty(&cfs_rq->throttled_csd_list)))
 		return;
 
 	first = list_empty(&rq->cfsb_csd_list);
@@ -6142,7 +6153,7 @@ static void unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq)
 {
 	lockdep_assert_rq_held(rq_of(cfs_rq));
 
-	if (SCHED_WARN_ON(!cfs_rq_throttled(cfs_rq) ||
+	if (WARN_ON_ONCE(!cfs_rq_throttled(cfs_rq) ||
 	    cfs_rq->runtime_remaining <= 0))
 		return;
 
@@ -6178,7 +6189,7 @@ static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
 			goto next;
 
 		/* By the above checks, this should never be true */
-		SCHED_WARN_ON(cfs_rq->runtime_remaining > 0);
+		WARN_ON_ONCE(cfs_rq->runtime_remaining > 0);
 
 		raw_spin_lock(&cfs_b->lock);
 		runtime = -cfs_rq->runtime_remaining + 1;
@@ -6199,7 +6210,7 @@ static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
 				 * We currently only expect to be unthrottling
 				 * a single cfs_rq locally.
 				 */
-				SCHED_WARN_ON(!list_empty(&local_unthrottle));
+				WARN_ON_ONCE(!list_empty(&local_unthrottle));
 				list_add_tail(&cfs_rq->throttled_csd_list,
 					      &local_unthrottle);
 			}
@@ -6224,7 +6235,7 @@ next:
 
 		rq_unlock_irqrestore(rq, &rf);
 	}
-	SCHED_WARN_ON(!list_empty(&local_unthrottle));
+	WARN_ON_ONCE(!list_empty(&local_unthrottle));
 
 	rcu_read_unlock();
 
@@ -6776,7 +6787,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
 
-	SCHED_WARN_ON(task_rq(p) != rq);
+	WARN_ON_ONCE(task_rq(p) != rq);
 
 	if (rq->cfs.h_nr_queued > 1) {
 		u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime;
@@ -6887,8 +6898,8 @@ requeue_delayed_entity(struct sched_entity *se)
 	 * Because a delayed entity is one that is still on
 	 * the runqueue competing until elegibility.
 	 */
-	SCHED_WARN_ON(!se->sched_delayed);
-	SCHED_WARN_ON(!se->on_rq);
+	WARN_ON_ONCE(!se->sched_delayed);
+	WARN_ON_ONCE(!se->on_rq);
 
 	if (sched_feat(DELAY_ZERO)) {
 		update_entity_lag(cfs_rq, se);
@@ -6991,6 +7002,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		update_cfs_group(se);
 
 		se->slice = slice;
+		if (se != cfs_rq->curr)
+			min_vruntime_cb_propagate(&se->run_node, NULL);
 		slice = cfs_rq_min_slice(cfs_rq);
 
 		cfs_rq->h_nr_runnable += h_nr_runnable;
@@ -7120,6 +7133,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 		update_cfs_group(se);
 
 		se->slice = slice;
+		if (se != cfs_rq->curr)
+			min_vruntime_cb_propagate(&se->run_node, NULL);
 		slice = cfs_rq_min_slice(cfs_rq);
 
 		cfs_rq->h_nr_runnable -= h_nr_runnable;
@@ -7144,8 +7159,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 		rq->next_balance = jiffies;
 
 	if (p && task_delayed) {
-		SCHED_WARN_ON(!task_sleep);
-		SCHED_WARN_ON(p->on_rq != 1);
+		WARN_ON_ONCE(!task_sleep);
+		WARN_ON_ONCE(p->on_rq != 1);
 
 		/* Fix-up what dequeue_task_fair() skipped */
 		hrtick_update(rq);
@@ -8723,7 +8738,7 @@ static inline void set_task_max_allowed_capacity(struct task_struct *p) {}
 static void set_next_buddy(struct sched_entity *se)
 {
 	for_each_sched_entity(se) {
-		if (SCHED_WARN_ON(!se->on_rq))
+		if (WARN_ON_ONCE(!se->on_rq))
 			return;
 		if (se_is_idle(se))
 			return;
@@ -8783,8 +8798,15 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	 * Preempt an idle entity in favor of a non-idle entity (and don't preempt
 	 * in the inverse case).
 	 */
-	if (cse_is_idle && !pse_is_idle)
+	if (cse_is_idle && !pse_is_idle) {
+		/*
+		 * When non-idle entity preempt an idle entity,
+		 * don't give idle entity slice protection.
+		 */
+		cancel_protect_slice(se);
 		goto preempt;
+	}
+
 	if (cse_is_idle != pse_is_idle)
 		return;
 
@@ -8803,8 +8825,8 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	 * Note that even if @p does not turn out to be the most eligible
 	 * task at this moment, current's slice protection will be lost.
 	 */
-	if (do_preempt_short(cfs_rq, pse, se) && se->vlag == se->deadline)
-		se->vlag = se->deadline + 1;
+	if (do_preempt_short(cfs_rq, pse, se))
+		cancel_protect_slice(se);
 
 	/*
 	 * If @p has become the most eligible task, force preemption.
@@ -9417,12 +9439,11 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 			return 0;
 
 		/* Prevent to re-select dst_cpu via env's CPUs: */
-		for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) {
-			if (cpumask_test_cpu(cpu, p->cpus_ptr)) {
-				env->flags |= LBF_DST_PINNED;
-				env->new_dst_cpu = cpu;
-				break;
-			}
+		cpu = cpumask_first_and_and(env->dst_grpmask, env->cpus, p->cpus_ptr);
+
+		if (cpu < nr_cpu_ids) {
+			env->flags |= LBF_DST_PINNED;
+			env->new_dst_cpu = cpu;
 		}
 
 		return 0;
@@ -12461,7 +12482,7 @@ unlock:
 
 void nohz_balance_exit_idle(struct rq *rq)
 {
-	SCHED_WARN_ON(rq != this_rq());
+	WARN_ON_ONCE(rq != this_rq());
 
 	if (likely(!rq->nohz_tick_stopped))
 		return;
@@ -12497,7 +12518,7 @@ void nohz_balance_enter_idle(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 
-	SCHED_WARN_ON(cpu != smp_processor_id());
+	WARN_ON_ONCE(cpu != smp_processor_id());
 
 	/* If this CPU is going down, then nothing needs to be done: */
 	if (!cpu_active(cpu))
@@ -12580,7 +12601,7 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags)
 	int balance_cpu;
 	struct rq *rq;
 
-	SCHED_WARN_ON((flags & NOHZ_KICK_MASK) == NOHZ_BALANCE_KICK);
+	WARN_ON_ONCE((flags & NOHZ_KICK_MASK) == NOHZ_BALANCE_KICK);
 
 	/*
 	 * We assume there will be no idle load after this update and clear
@@ -13020,7 +13041,7 @@ bool cfs_prio_less(const struct task_struct *a, const struct task_struct *b,
 	struct cfs_rq *cfs_rqb;
 	s64 delta;
 
-	SCHED_WARN_ON(task_rq(b)->core != rq->core);
+	WARN_ON_ONCE(task_rq(b)->core != rq->core);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/*
@@ -13223,7 +13244,7 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
 
 static void switched_to_fair(struct rq *rq, struct task_struct *p)
 {
-	SCHED_WARN_ON(p->se.sched_delayed);
+	WARN_ON_ONCE(p->se.sched_delayed);
 
 	attach_task_cfs_rq(p);
 
@@ -13258,7 +13279,7 @@ static void __set_next_task_fair(struct rq *rq, struct task_struct *p, bool firs
 	if (!first)
 		return;
 
-	SCHED_WARN_ON(se->sched_delayed);
+	WARN_ON_ONCE(se->sched_delayed);
 
 	if (hrtick_enabled_fair(rq))
 		hrtick_start_fair(rq, p);
@@ -13645,7 +13666,6 @@ DEFINE_SCHED_CLASS(fair) = {
 #endif
 };
 
-#ifdef CONFIG_SCHED_DEBUG
 void print_cfs_stats(struct seq_file *m, int cpu)
 {
 	struct cfs_rq *cfs_rq, *pos;
@@ -13679,7 +13699,6 @@ void show_numa_stats(struct task_struct *p, struct seq_file *m)
 	rcu_read_unlock();
 }
 #endif /* CONFIG_NUMA_BALANCING */
-#endif /* CONFIG_SCHED_DEBUG */
 
 __init void init_sched_fair_class(void)
 {
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 4b8e33c615b1..a4774155ae12 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -169,9 +169,8 @@ static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
 
 static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
 {
-#ifdef CONFIG_SCHED_DEBUG
 	WARN_ON_ONCE(!rt_entity_is_task(rt_se));
-#endif
+
 	return container_of(rt_se, struct task_struct, rt);
 }
 
@@ -1713,7 +1712,7 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq)
 	BUG_ON(idx >= MAX_RT_PRIO);
 
 	queue = array->queue + idx;
-	if (SCHED_WARN_ON(list_empty(queue)))
+	if (WARN_ON_ONCE(list_empty(queue)))
 		return NULL;
 	next = list_entry(queue->next, struct sched_rt_entity, run_list);
 
@@ -2910,6 +2909,7 @@ static int sched_rt_handler(const struct ctl_table *table, int write, void *buff
 	int ret;
 
 	mutex_lock(&mutex);
+	sched_domains_mutex_lock();
 	old_period = sysctl_sched_rt_period;
 	old_runtime = sysctl_sched_rt_runtime;
 
@@ -2936,6 +2936,7 @@ undo:
 		sysctl_sched_rt_period = old_period;
 		sysctl_sched_rt_runtime = old_runtime;
 	}
+	sched_domains_mutex_unlock();
 	mutex_unlock(&mutex);
 
 	return ret;
@@ -2967,7 +2968,6 @@ static int sched_rr_handler(const struct ctl_table *table, int write, void *buff
 }
 #endif /* CONFIG_SYSCTL */
 
-#ifdef CONFIG_SCHED_DEBUG
 void print_rt_stats(struct seq_file *m, int cpu)
 {
 	rt_rq_iter_t iter;
@@ -2978,4 +2978,3 @@ void print_rt_stats(struct seq_file *m, int cpu)
 		print_rt_rq(m, cpu, rt_rq);
 	rcu_read_unlock();
 }
-#endif /* CONFIG_SCHED_DEBUG */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 023b844159c9..47972f34ea70 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -91,12 +91,6 @@ struct cpuidle_state;
 #include "cpupri.h"
 #include "cpudeadline.h"
 
-#ifdef CONFIG_SCHED_DEBUG
-# define SCHED_WARN_ON(x)      WARN_ONCE(x, #x)
-#else
-# define SCHED_WARN_ON(x)      ({ (void)(x), 0; })
-#endif
-
 /* task_struct::on_rq states: */
 #define TASK_ON_RQ_QUEUED	1
 #define TASK_ON_RQ_MIGRATING	2
@@ -998,7 +992,7 @@ struct root_domain {
 	 * Also, some corner cases, like 'wrap around' is dangerous, but given
 	 * that u64 is 'big enough'. So that shouldn't be a concern.
 	 */
-	u64 visit_gen;
+	u64 visit_cookie;
 
 #ifdef HAVE_RT_PUSH_IPI
 	/*
@@ -1180,10 +1174,8 @@ struct rq {
 
 	atomic_t		nr_iowait;
 
-#ifdef CONFIG_SCHED_DEBUG
 	u64 last_seen_need_resched_ns;
 	int ticks_without_resched;
-#endif
 
 #ifdef CONFIG_MEMBARRIER
 	int membarrier_state;
@@ -1571,7 +1563,7 @@ static inline void update_idle_core(struct rq *rq) { }
 
 static inline struct task_struct *task_of(struct sched_entity *se)
 {
-	SCHED_WARN_ON(!entity_is_task(se));
+	WARN_ON_ONCE(!entity_is_task(se));
 	return container_of(se, struct task_struct, se);
 }
 
@@ -1652,7 +1644,7 @@ static inline void assert_clock_updated(struct rq *rq)
 	 * The only reason for not seeing a clock update since the
 	 * last rq_pin_lock() is if we're currently skipping updates.
 	 */
-	SCHED_WARN_ON(rq->clock_update_flags < RQCF_ACT_SKIP);
+	WARN_ON_ONCE(rq->clock_update_flags < RQCF_ACT_SKIP);
 }
 
 static inline u64 rq_clock(struct rq *rq)
@@ -1699,7 +1691,7 @@ static inline void rq_clock_cancel_skipupdate(struct rq *rq)
 static inline void rq_clock_start_loop_update(struct rq *rq)
 {
 	lockdep_assert_rq_held(rq);
-	SCHED_WARN_ON(rq->clock_update_flags & RQCF_ACT_SKIP);
+	WARN_ON_ONCE(rq->clock_update_flags & RQCF_ACT_SKIP);
 	rq->clock_update_flags |= RQCF_ACT_SKIP;
 }
 
@@ -1712,14 +1704,12 @@ static inline void rq_clock_stop_loop_update(struct rq *rq)
 struct rq_flags {
 	unsigned long flags;
 	struct pin_cookie cookie;
-#ifdef CONFIG_SCHED_DEBUG
 	/*
 	 * A copy of (rq::clock_update_flags & RQCF_UPDATED) for the
 	 * current pin context is stashed here in case it needs to be
 	 * restored in rq_repin_lock().
 	 */
 	unsigned int clock_update_flags;
-#endif
 };
 
 extern struct balance_callback balance_push_callback;
@@ -1770,21 +1760,18 @@ static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
 {
 	rf->cookie = lockdep_pin_lock(__rq_lockp(rq));
 
-#ifdef CONFIG_SCHED_DEBUG
 	rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
 	rf->clock_update_flags = 0;
-# ifdef CONFIG_SMP
-	SCHED_WARN_ON(rq->balance_callback && rq->balance_callback != &balance_push_callback);
-# endif
+#ifdef CONFIG_SMP
+	WARN_ON_ONCE(rq->balance_callback && rq->balance_callback != &balance_push_callback);
 #endif
 }
 
 static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf)
 {
-#ifdef CONFIG_SCHED_DEBUG
 	if (rq->clock_update_flags > RQCF_ACT_SKIP)
 		rf->clock_update_flags = RQCF_UPDATED;
-#endif
+
 	scx_rq_clock_invalidate(rq);
 	lockdep_unpin_lock(__rq_lockp(rq), rf->cookie);
 }
@@ -1793,12 +1780,10 @@ static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf)
 {
 	lockdep_repin_lock(__rq_lockp(rq), rf->cookie);
 
-#ifdef CONFIG_SCHED_DEBUG
 	/*
 	 * Restore the value we stashed in @rf for this pin context.
 	 */
 	rq->clock_update_flags |= rf->clock_update_flags;
-#endif
 }
 
 extern
@@ -2072,9 +2057,7 @@ struct sched_group_capacity {
 	unsigned long		next_update;
 	int			imbalance;		/* XXX unrelated to capacity but shared group state */
 
-#ifdef CONFIG_SCHED_DEBUG
 	int			id;
-#endif
 
 	unsigned long		cpumask[];		/* Balance mask */
 };
@@ -2114,13 +2097,8 @@ static inline struct cpumask *group_balance_mask(struct sched_group *sg)
 
 extern int group_balance_cpu(struct sched_group *sg);
 
-#ifdef CONFIG_SCHED_DEBUG
 extern void update_sched_domain_debugfs(void);
 extern void dirty_sched_domain_sysctl(int cpu);
-#else
-static inline void update_sched_domain_debugfs(void) { }
-static inline void dirty_sched_domain_sysctl(int cpu) { }
-#endif
 
 extern int sched_update_scaling(void);
 
@@ -2200,13 +2178,8 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 }
 
 /*
- * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
+ * Tunables:
  */
-#ifdef CONFIG_SCHED_DEBUG
-# define const_debug __read_mostly
-#else
-# define const_debug const
-#endif
 
 #define SCHED_FEAT(name, enabled)	\
 	__SCHED_FEAT_##name ,
@@ -2218,13 +2191,11 @@ enum {
 
 #undef SCHED_FEAT
 
-#ifdef CONFIG_SCHED_DEBUG
-
 /*
  * To support run-time toggling of sched features, all the translation units
  * (but core.c) reference the sysctl_sched_features defined in core.c.
  */
-extern const_debug unsigned int sysctl_sched_features;
+extern __read_mostly unsigned int sysctl_sched_features;
 
 #ifdef CONFIG_JUMP_LABEL
 
@@ -2246,24 +2217,6 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
 
 #endif /* !CONFIG_JUMP_LABEL */
 
-#else /* !SCHED_DEBUG: */
-
-/*
- * Each translation unit has its own copy of sysctl_sched_features to allow
- * constants propagation at compile time and compiler optimization based on
- * features default.
- */
-#define SCHED_FEAT(name, enabled)	\
-	(1UL << __SCHED_FEAT_##name) * enabled |
-static const_debug __maybe_unused unsigned int sysctl_sched_features =
-#include "features.h"
-	0;
-#undef SCHED_FEAT
-
-#define sched_feat(x) !!(sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
-
-#endif /* !SCHED_DEBUG */
-
 extern struct static_key_false sched_numa_balancing;
 extern struct static_key_false sched_schedstats;
 
@@ -2685,7 +2638,7 @@ static inline void idle_set_state(struct rq *rq,
 
 static inline struct cpuidle_state *idle_get_state(struct rq *rq)
 {
-	SCHED_WARN_ON(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	return rq->idle_state;
 }
@@ -2843,12 +2796,11 @@ extern void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags);
 # 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;
+extern __read_mostly unsigned int sysctl_sched_nr_migrate;
+extern __read_mostly unsigned int sysctl_sched_migration_cost;
 
 extern unsigned int sysctl_sched_base_slice;
 
-#ifdef CONFIG_SCHED_DEBUG
 extern int sysctl_resched_latency_warn_ms;
 extern int sysctl_resched_latency_warn_once;
 
@@ -2859,7 +2811,6 @@ 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
 
@@ -2932,7 +2883,6 @@ 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
@@ -2947,9 +2897,6 @@ static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2)
 	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
 
 #define DEFINE_LOCK_GUARD_2(name, type, _lock, _unlock, ...)				\
 __DEFINE_UNLOCK_GUARD(name, type, _unlock, type *lock2; __VA_ARGS__)			\
@@ -3162,7 +3109,6 @@ extern struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq);
 extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
 extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
 
-#ifdef	CONFIG_SCHED_DEBUG
 extern bool sched_debug_verbose;
 
 extern void print_cfs_stats(struct seq_file *m, int cpu);
@@ -3173,15 +3119,12 @@ extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
 extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
 
 extern void resched_latency_warn(int cpu, u64 latency);
-# ifdef CONFIG_NUMA_BALANCING
+#ifdef CONFIG_NUMA_BALANCING
 extern void show_numa_stats(struct task_struct *p, struct seq_file *m);
 extern void
 print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
 		 unsigned long tpf, unsigned long gsf, unsigned long gpf);
-# endif /* CONFIG_NUMA_BALANCING */
-#else /* !CONFIG_SCHED_DEBUG: */
-static inline void resched_latency_warn(int cpu, u64 latency) { }
-#endif /* !CONFIG_SCHED_DEBUG */
+#endif /* CONFIG_NUMA_BALANCING */
 
 extern void init_cfs_rq(struct cfs_rq *cfs_rq);
 extern void init_rt_rq(struct rt_rq *rt_rq);
@@ -3394,6 +3337,31 @@ static inline bool update_other_load_avgs(struct rq *rq) { return false; }
 
 unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
 
+/*
+ * 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);
+}
+
+/*
+ * Enabling static branches would get the cpus_read_lock(),
+ * check whether uclamp_is_used before enable it to avoid always
+ * calling cpus_read_lock(). Because we never disable this
+ * static key once enable it.
+ */
+static inline void sched_uclamp_enable(void)
+{
+	if (!uclamp_is_used())
+		static_branch_enable(&sched_uclamp_used);
+}
+
 static inline unsigned long uclamp_rq_get(struct rq *rq,
 					  enum uclamp_id clamp_id)
 {
@@ -3417,7 +3385,7 @@ 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))
+	if (!uclamp_is_used())
 		return false;
 
 	rq_util = cpu_util_cfs(cpu_of(rq)) + cpu_util_rt(rq);
@@ -3426,19 +3394,6 @@ static inline bool uclamp_rq_is_capped(struct rq *rq)
 	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);
-}
-
 #define for_each_clamp_id(clamp_id) \
 	for ((clamp_id) = 0; (clamp_id) < UCLAMP_CNT; (clamp_id)++)
 
@@ -3486,6 +3441,8 @@ static inline bool uclamp_is_used(void)
 	return false;
 }
 
+static inline void sched_uclamp_enable(void) {}
+
 static inline unsigned long
 uclamp_rq_get(struct rq *rq, enum uclamp_id clamp_id)
 {
@@ -3619,6 +3576,7 @@ extern int preempt_dynamic_mode;
 extern int sched_dynamic_mode(const char *str);
 extern void sched_dynamic_update(int mode);
 #endif
+extern const char *preempt_modes[];
 
 #ifdef CONFIG_SCHED_MM_CID
 
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 19cdbe96f93d..452826df6ae1 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -144,7 +144,7 @@ static inline void psi_enqueue(struct task_struct *p, int flags)
 
 	if (p->se.sched_delayed) {
 		/* CPU migration of "sleeping" task */
-		SCHED_WARN_ON(!(flags & ENQUEUE_MIGRATED));
+		WARN_ON_ONCE(!(flags & ENQUEUE_MIGRATED));
 		if (p->in_memstall)
 			set |= TSK_MEMSTALL;
 		if (p->in_iowait)
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 456d339be98f..c326de1344fb 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -368,7 +368,7 @@ static int uclamp_validate(struct task_struct *p,
 	 * blocking operation which obviously cannot be done while holding
 	 * scheduler locks.
 	 */
-	static_branch_enable(&sched_uclamp_used);
+	sched_uclamp_enable();
 
 	return 0;
 }
@@ -875,7 +875,7 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 {
 	struct sched_param lparam;
 
-	if (!param || pid < 0)
+	if (unlikely(!param || pid < 0))
 		return -EINVAL;
 	if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
 		return -EFAULT;
@@ -984,7 +984,7 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 	struct sched_attr attr;
 	int retval;
 
-	if (!uattr || pid < 0 || flags)
+	if (unlikely(!uattr || pid < 0 || flags))
 		return -EINVAL;
 
 	retval = sched_copy_attr(uattr, &attr);
@@ -1049,7 +1049,7 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 	struct task_struct *p;
 	int retval;
 
-	if (!param || pid < 0)
+	if (unlikely(!param || pid < 0))
 		return -EINVAL;
 
 	scoped_guard (rcu) {
@@ -1085,8 +1085,8 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	struct task_struct *p;
 	int retval;
 
-	if (!uattr || pid < 0 || usize > PAGE_SIZE ||
-	    usize < SCHED_ATTR_SIZE_VER0 || flags)
+	if (unlikely(!uattr || pid < 0 || usize > PAGE_SIZE ||
+		      usize < SCHED_ATTR_SIZE_VER0 || flags))
 		return -EINVAL;
 
 	scoped_guard (rcu) {
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index c49aea8c1025..f1ebc60d967f 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -6,13 +6,19 @@
 #include <linux/bsearch.h>
 
 DEFINE_MUTEX(sched_domains_mutex);
+void sched_domains_mutex_lock(void)
+{
+	mutex_lock(&sched_domains_mutex);
+}
+void sched_domains_mutex_unlock(void)
+{
+	mutex_unlock(&sched_domains_mutex);
+}
 
 /* Protected by sched_domains_mutex: */
 static cpumask_var_t sched_domains_tmpmask;
 static cpumask_var_t sched_domains_tmpmask2;
 
-#ifdef CONFIG_SCHED_DEBUG
-
 static int __init sched_debug_setup(char *str)
 {
 	sched_debug_verbose = true;
@@ -151,15 +157,6 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 			break;
 	}
 }
-#else /* !CONFIG_SCHED_DEBUG */
-
-# define sched_debug_verbose 0
-# define sched_domain_debug(sd, cpu) do { } while (0)
-static inline bool sched_debug(void)
-{
-	return false;
-}
-#endif /* CONFIG_SCHED_DEBUG */
 
 /* Generate a mask of SD flags with the SDF_NEEDS_GROUPS metaflag */
 #define SD_FLAG(name, mflags) (name * !!((mflags) & SDF_NEEDS_GROUPS)) |
@@ -560,7 +557,7 @@ static int init_rootdomain(struct root_domain *rd)
 	rd->rto_push_work = IRQ_WORK_INIT_HARD(rto_push_irq_work_func);
 #endif
 
-	rd->visit_gen = 0;
+	rd->visit_cookie = 0;
 	init_dl_bw(&rd->dl_bw);
 	if (cpudl_init(&rd->cpudl) != 0)
 		goto free_rto_mask;
@@ -2275,9 +2272,7 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 			if (!sgc)
 				return -ENOMEM;
 
-#ifdef CONFIG_SCHED_DEBUG
 			sgc->id = j;
-#endif
 
 			*per_cpu_ptr(sdd->sgc, j) = sgc;
 		}
@@ -2680,7 +2675,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
  *
  * Call with hotplug lock and sched_domains_mutex held
  */
-void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
+static void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
 				    struct sched_domain_attr *dattr_new)
 {
 	bool __maybe_unused has_eas = false;
@@ -2712,21 +2707,8 @@ void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
 	for (i = 0; i < ndoms_cur; i++) {
 		for (j = 0; j < n && !new_topology; j++) {
 			if (cpumask_equal(doms_cur[i], doms_new[j]) &&
-			    dattrs_equal(dattr_cur, i, dattr_new, j)) {
-				struct root_domain *rd;
-
-				/*
-				 * This domain won't be destroyed and as such
-				 * its dl_bw->total_bw needs to be cleared.
-				 * Tasks contribution will be then recomputed
-				 * in function dl_update_tasks_root_domain(),
-				 * dl_servers contribution in function
-				 * dl_restore_server_root_domain().
-				 */
-				rd = cpu_rq(cpumask_any(doms_cur[i]))->rd;
-				dl_clear_root_domain(rd);
+			    dattrs_equal(dattr_cur, i, dattr_new, j))
 				goto match1;
-			}
 		}
 		/* No match - a current sched domain not in new doms_new[] */
 		detach_destroy_domains(doms_cur[i]);
@@ -2783,6 +2765,7 @@ match3:
 	ndoms_cur = ndoms_new;
 
 	update_sched_domain_debugfs();
+	dl_rebuild_rd_accounting();
 }
 
 /*
@@ -2791,7 +2774,7 @@ match3:
 void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 			     struct sched_domain_attr *dattr_new)
 {
-	mutex_lock(&sched_domains_mutex);
+	sched_domains_mutex_lock();
 	partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
-	mutex_unlock(&sched_domains_mutex);
+	sched_domains_mutex_unlock();
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0e6d517e74e0..fd3cb2b2ab82 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4100,12 +4100,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 		   entries,
 		   total,
 		   buf->cpu,
-		   preempt_model_none()      ? "server" :
-		   preempt_model_voluntary() ? "desktop" :
-		   preempt_model_full()      ? "preempt" :
-		   preempt_model_lazy()	     ? "lazy"    :
-		   preempt_model_rt()        ? "preempt_rt" :
-		   "unknown",
+		   preempt_model_str(),
 		   /* These are reserved for later use */
 		   0, 0, 0, 0);
 #ifdef CONFIG_SMP