17 files changed, 175 insertions, 191 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 75c151413fda..0d1ada8968d7 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -450,6 +450,7 @@ extern struct mutex cgroup_mutex;
 extern spinlock_t css_set_lock;
 #define task_css_set_check(task, __c)					\
 	rcu_dereference_check((task)->cgroups,				\
+		rcu_read_lock_sched_held() ||				\
 		lockdep_is_held(&cgroup_mutex) ||			\
 		lockdep_is_held(&css_set_lock) ||			\
 		((task)->flags & PF_EXITING) || (__c))
@@ -791,11 +792,9 @@ static inline void cgroup_account_cputime(struct task_struct *task,
 
 	cpuacct_charge(task, delta_exec);
 
-	rcu_read_lock();
 	cgrp = task_dfl_cgroup(task);
 	if (cgroup_parent(cgrp))
 		__cgroup_account_cputime(cgrp, delta_exec);
-	rcu_read_unlock();
 }
 
 static inline void cgroup_account_cputime_field(struct task_struct *task,
@@ -806,11 +805,9 @@ static inline void cgroup_account_cputime_field(struct task_struct *task,
 
 	cpuacct_account_field(task, index, delta_exec);
 
-	rcu_read_lock();
 	cgrp = task_dfl_cgroup(task);
 	if (cgroup_parent(cgrp))
 		__cgroup_account_cputime_field(cgrp, index, delta_exec);
-	rcu_read_unlock();
 }
 
 #else	/* CONFIG_CGROUPS */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f00132e7ef6e..78b606c9ab38 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1620,19 +1620,32 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk)
 #define TASK_REPORT_IDLE	(TASK_REPORT + 1)
 #define TASK_REPORT_MAX		(TASK_REPORT_IDLE << 1)
 
-static inline unsigned int task_state_index(struct task_struct *tsk)
+static inline unsigned int __task_state_index(unsigned int tsk_state,
+					      unsigned int tsk_exit_state)
 {
-	unsigned int tsk_state = READ_ONCE(tsk->__state);
-	unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT;
+	unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT;
 
 	BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX);
 
 	if (tsk_state == TASK_IDLE)
 		state = TASK_REPORT_IDLE;
 
+	/*
+	 * We're lying here, but rather than expose a completely new task state
+	 * to userspace, we can make this appear as if the task has gone through
+	 * a regular rt_mutex_lock() call.
+	 */
+	if (tsk_state == TASK_RTLOCK_WAIT)
+		state = TASK_UNINTERRUPTIBLE;
+
 	return fls(state);
 }
 
+static inline unsigned int task_state_index(struct task_struct *tsk)
+{
+	return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state);
+}
+
 static inline char task_index_to_char(unsigned int state)
 {
 	static const char state_char[] = "RSDTtXZPI";
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 94640482cfe7..65e786756321 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -187,7 +187,9 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
 	     TP_ARGS(p));
 
 #ifdef CREATE_TRACE_POINTS
-static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p)
+static inline long __trace_sched_switch_state(bool preempt,
+					      unsigned int prev_state,
+					      struct task_struct *p)
 {
 	unsigned int state;
 
@@ -208,7 +210,7 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct *
 	 * it for left shift operation to get the correct task->state
 	 * mapping.
 	 */
-	state = task_state_index(p);
+	state = __task_state_index(prev_state, p->exit_state);
 
 	return state ? (1 << (state - 1)) : state;
 }
@@ -220,10 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct *
 TRACE_EVENT(sched_switch,
 
 	TP_PROTO(bool preempt,
+		 unsigned int prev_state,
 		 struct task_struct *prev,
 		 struct task_struct *next),
 
-	TP_ARGS(preempt, prev, next),
+	TP_ARGS(preempt, prev_state, prev, next),
 
 	TP_STRUCT__entry(
 		__array(	char,	prev_comm,	TASK_COMM_LEN	)
@@ -239,7 +242,7 @@ TRACE_EVENT(sched_switch,
 		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
 		__entry->prev_pid	= prev->pid;
 		__entry->prev_prio	= prev->prio;
-		__entry->prev_state	= __trace_sched_switch_state(preempt, prev);
+		__entry->prev_state	= __trace_sched_switch_state(preempt, prev_state, prev);
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
 		__entry->next_pid	= next->pid;
 		__entry->next_prio	= next->prio;
diff --git a/init/Makefile b/init/Makefile
index 06326e304384..d82623d7fc8e 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -31,7 +31,8 @@ quiet_cmd_compile.h = CHK     $@
       cmd_compile.h = \
 	$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@	\
 	"$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT_BUILD)"	\
-	"$(CONFIG_PREEMPT_RT)" "$(CONFIG_CC_VERSION_TEXT)" "$(LD)"
+	"$(CONFIG_PREEMPT_DYNAMIC)" "$(CONFIG_PREEMPT_RT)" \
+	"$(CONFIG_CC_VERSION_TEXT)" "$(LD)"
 
 include/generated/compile.h: FORCE
 	$(call cmd,compile.h)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5eaa4211d93c..aa9e14ce94fb 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4897,7 +4897,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 {
 	struct rq *rq = this_rq();
 	struct mm_struct *mm = rq->prev_mm;
-	long prev_state;
+	unsigned int prev_state;
 
 	/*
 	 * The previous task will have left us with a preempt_count of 2
@@ -6361,7 +6361,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		migrate_disable_switch(rq, prev);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
-		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next);
+		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev_state, prev, next);
 
 		/* Also unlocks the rq: */
 		rq = context_switch(rq, prev, next, &rf);
@@ -8866,8 +8866,11 @@ int task_can_attach(struct task_struct *p,
 	}
 
 	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
-					      cs_cpus_allowed))
-		ret = dl_task_can_attach(p, cs_cpus_allowed);
+					      cs_cpus_allowed)) {
+		int cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed);
+
+		ret = dl_cpu_busy(cpu, p);
+	}
 
 out:
 	return ret;
@@ -9151,8 +9154,10 @@ static void cpuset_cpu_active(void)
 static int cpuset_cpu_inactive(unsigned int cpu)
 {
 	if (!cpuhp_tasks_frozen) {
-		if (dl_cpu_busy(cpu))
-			return -EBUSY;
+		int ret = dl_cpu_busy(cpu, NULL);
+
+		if (ret)
+			return ret;
 		cpuset_update_active_cpus();
 	} else {
 		num_cpus_frozen++;
@@ -9481,7 +9486,6 @@ void __init sched_init(void)
 #endif /* CONFIG_CPUMASK_OFFSTACK */
 
 	init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
-	init_dl_bandwidth(&def_dl_bandwidth, global_rt_period(), global_rt_runtime());
 
 #ifdef CONFIG_SMP
 	init_defrootdomain();
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 2c505cf800aa..0de9dda09949 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -333,14 +333,13 @@ static struct cftype files[] = {
  */
 void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 {
+	unsigned int cpu = task_cpu(tsk);
 	struct cpuacct *ca;
 
-	rcu_read_lock();
+	lockdep_assert_rq_held(cpu_rq(cpu));
 
 	for (ca = task_ca(tsk); ca; ca = parent_ca(ca))
-		__this_cpu_add(*ca->cpuusage, cputime);
-
-	rcu_read_unlock();
+		*per_cpu_ptr(ca->cpuusage, cpu) += cputime;
 }
 
 /*
@@ -352,10 +351,8 @@ void cpuacct_account_field(struct task_struct *tsk, int index, u64 val)
 {
 	struct cpuacct *ca;
 
-	rcu_read_lock();
 	for (ca = task_ca(tsk); ca != &root_cpuacct; ca = parent_ca(ca))
 		__this_cpu_add(ca->cpustat->cpustat[index], val);
-	rcu_read_unlock();
 }
 
 struct cgroup_subsys cpuacct_cgrp_subsys = {
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fca2d7de4d3d..fb4255ae0b2c 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -16,8 +16,6 @@
  *                    Fabio Checconi <[email protected]>
  */
 
-struct dl_bandwidth def_dl_bandwidth;
-
 static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
 {
 	return container_of(dl_se, struct task_struct, dl);
@@ -128,6 +126,21 @@ static inline bool dl_bw_visited(int cpu, u64 gen)
 	rd->visit_gen = gen;
 	return false;
 }
+
+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 struct dl_bw *dl_bw_of(int i)
 {
@@ -148,9 +161,38 @@ static inline bool dl_bw_visited(int cpu, u64 gen)
 {
 	return false;
 }
+
+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
 
 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;
+}
+
+static inline
 void __add_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
 {
 	u64 old = dl_rq->running_bw;
@@ -406,7 +448,7 @@ static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
 {
 	struct sched_dl_entity *dl_se = &p->dl;
 
-	return dl_rq->root.rb_leftmost == &dl_se->rb_node;
+	return rb_first_cached(&dl_rq->root) == &dl_se->rb_node;
 }
 
 static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
@@ -421,12 +463,10 @@ void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime)
 void init_dl_bw(struct dl_bw *dl_b)
 {
 	raw_spin_lock_init(&dl_b->lock);
-	raw_spin_lock(&def_dl_bandwidth.dl_runtime_lock);
 	if (global_rt_runtime() == RUNTIME_INF)
 		dl_b->bw = -1;
 	else
 		dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime());
-	raw_spin_unlock(&def_dl_bandwidth.dl_runtime_lock);
 	dl_b->total_bw = 0;
 }
 
@@ -681,15 +721,6 @@ void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 }
 
-static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
-{
-	return false;
-}
-
-static inline void pull_dl_task(struct rq *rq)
-{
-}
-
 static inline void deadline_queue_push_tasks(struct rq *rq)
 {
 }
@@ -1391,6 +1422,9 @@ void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
 	timer->function = inactive_task_timer;
 }
 
+#define __node_2_dle(node) \
+	rb_entry((node), struct sched_dl_entity, rb_node)
+
 #ifdef CONFIG_SMP
 
 static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
@@ -1420,10 +1454,9 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 		cpudl_clear(&rq->rd->cpudl, rq->cpu);
 		cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
 	} else {
-		struct rb_node *leftmost = dl_rq->root.rb_leftmost;
-		struct sched_dl_entity *entry;
+		struct rb_node *leftmost = rb_first_cached(&dl_rq->root);
+		struct sched_dl_entity *entry = __node_2_dle(leftmost);
 
-		entry = rb_entry(leftmost, struct sched_dl_entity, rb_node);
 		dl_rq->earliest_dl.curr = entry->deadline;
 		cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline);
 	}
@@ -1464,9 +1497,6 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 	dec_dl_migration(dl_se, dl_rq);
 }
 
-#define __node_2_dle(node) \
-	rb_entry((node), struct sched_dl_entity, rb_node)
-
 static inline bool __dl_less(struct rb_node *a, const struct rb_node *b)
 {
 	return dl_time_before(__node_2_dle(a)->deadline, __node_2_dle(b)->deadline);
@@ -1929,15 +1959,14 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
 	deadline_queue_push_tasks(rq);
 }
 
-static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
-						   struct dl_rq *dl_rq)
+static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq)
 {
 	struct rb_node *left = rb_first_cached(&dl_rq->root);
 
 	if (!left)
 		return NULL;
 
-	return rb_entry(left, struct sched_dl_entity, rb_node);
+	return __node_2_dle(left);
 }
 
 static struct task_struct *pick_task_dl(struct rq *rq)
@@ -1949,7 +1978,7 @@ static struct task_struct *pick_task_dl(struct rq *rq)
 	if (!sched_dl_runnable(rq))
 		return NULL;
 
-	dl_se = pick_next_dl_entity(rq, dl_rq);
+	dl_se = pick_next_dl_entity(dl_rq);
 	BUG_ON(!dl_se);
 	p = dl_task_of(dl_se);
 
@@ -2032,15 +2061,17 @@ static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
  */
 static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu)
 {
-	struct rb_node *next_node = rq->dl.pushable_dl_tasks_root.rb_leftmost;
 	struct task_struct *p = NULL;
+	struct rb_node *next_node;
 
 	if (!has_pushable_dl_tasks(rq))
 		return NULL;
 
+	next_node = rb_first_cached(&rq->dl.pushable_dl_tasks_root);
+
 next_node:
 	if (next_node) {
-		p = rb_entry(next_node, struct task_struct, pushable_dl_tasks);
+		p = __node_2_pdl(next_node);
 
 		if (pick_dl_task(rq, p, cpu))
 			return p;
@@ -2206,8 +2237,7 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
 	if (!has_pushable_dl_tasks(rq))
 		return NULL;
 
-	p = rb_entry(rq->dl.pushable_dl_tasks_root.rb_leftmost,
-		     struct task_struct, pushable_dl_tasks);
+	p = __node_2_pdl(rb_first_cached(&rq->dl.pushable_dl_tasks_root));
 
 	BUG_ON(rq->cpu != task_cpu(p));
 	BUG_ON(task_current(rq, p));
@@ -2238,12 +2268,6 @@ static int push_dl_task(struct rq *rq)
 		return 0;
 
 retry:
-	if (is_migration_disabled(next_task))
-		return 0;
-
-	if (WARN_ON(next_task == rq->curr))
-		return 0;
-
 	/*
 	 * If next_task preempts rq->curr, and rq->curr
 	 * can move away, it makes sense to just reschedule
@@ -2256,6 +2280,12 @@ retry:
 		return 0;
 	}
 
+	if (is_migration_disabled(next_task))
+		return 0;
+
+	if (WARN_ON(next_task == rq->curr))
+		return 0;
+
 	/* We might release rq lock */
 	get_task_struct(next_task);
 
@@ -2729,9 +2759,6 @@ void sched_dl_do_global(void)
 	int cpu;
 	unsigned long flags;
 
-	def_dl_bandwidth.dl_period = global_rt_period();
-	def_dl_bandwidth.dl_runtime = global_rt_runtime();
-
 	if (global_rt_runtime() != RUNTIME_INF)
 		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
 
@@ -2953,41 +2980,6 @@ bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
 }
 
 #ifdef CONFIG_SMP
-int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed)
-{
-	unsigned long flags, cap;
-	unsigned int dest_cpu;
-	struct dl_bw *dl_b;
-	bool overflow;
-	int ret;
-
-	dest_cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed);
-
-	rcu_read_lock_sched();
-	dl_b = dl_bw_of(dest_cpu);
-	raw_spin_lock_irqsave(&dl_b->lock, flags);
-	cap = dl_bw_capacity(dest_cpu);
-	overflow = __dl_overflow(dl_b, cap, 0, p->dl.dl_bw);
-	if (overflow) {
-		ret = -EBUSY;
-	} else {
-		/*
-		 * We reserve space for this task in the destination
-		 * root_domain, as we can't fail after this point.
-		 * We will free resources in the source root_domain
-		 * later on (see set_cpus_allowed_dl()).
-		 */
-		int cpus = dl_bw_cpus(dest_cpu);
-
-		__dl_add(dl_b, p->dl.dl_bw, cpus);
-		ret = 0;
-	}
-	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-	rcu_read_unlock_sched();
-
-	return ret;
-}
-
 int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
 				 const struct cpumask *trial)
 {
@@ -3009,7 +3001,7 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
 	return ret;
 }
 
-bool dl_cpu_busy(unsigned int cpu)
+int dl_cpu_busy(int cpu, struct task_struct *p)
 {
 	unsigned long flags, cap;
 	struct dl_bw *dl_b;
@@ -3019,11 +3011,22 @@ bool dl_cpu_busy(unsigned int cpu)
 	dl_b = dl_bw_of(cpu);
 	raw_spin_lock_irqsave(&dl_b->lock, flags);
 	cap = dl_bw_capacity(cpu);
-	overflow = __dl_overflow(dl_b, cap, 0, 0);
+	overflow = __dl_overflow(dl_b, cap, 0, p ? p->dl.dl_bw : 0);
+
+	if (!overflow && p) {
+		/*
+		 * We reserve space for this task in the destination
+		 * root_domain, as we can't fail after this point.
+		 * We will free resources in the source root_domain
+		 * later on (see set_cpus_allowed_dl()).
+		 */
+		__dl_add(dl_b, p->dl.dl_bw, dl_bw_cpus(cpu));
+	}
+
 	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 	rcu_read_unlock_sched();
 
-	return overflow;
+	return overflow ? -EBUSY : 0;
 }
 #endif
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index ff4c044aed12..a32c46889af8 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -268,8 +268,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 
 #ifdef CONFIG_SMP
 
-static void pull_rt_task(struct rq *this_rq);
-
 static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
 {
 	/* Try to pull RT tasks here if we lower this rq's prio */
@@ -426,15 +424,6 @@ void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
 }
 
-static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
-{
-	return false;
-}
-
-static inline void pull_rt_task(struct rq *this_rq)
-{
-}
-
 static inline void rt_queue_push_tasks(struct rq *rq)
 {
 }
@@ -1727,8 +1716,7 @@ static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool f
 	rt_queue_push_tasks(rq);
 }
 
-static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
-						   struct rt_rq *rt_rq)
+static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq)
 {
 	struct rt_prio_array *array = &rt_rq->active;
 	struct sched_rt_entity *next = NULL;
@@ -1750,7 +1738,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 	struct rt_rq *rt_rq  = &rq->rt;
 
 	do {
-		rt_se = pick_next_rt_entity(rq, rt_rq);
+		rt_se = pick_next_rt_entity(rt_rq);
 		BUG_ON(!rt_se);
 		rt_rq = group_rt_rq(rt_se);
 	} while (rt_rq);
@@ -2023,6 +2011,16 @@ static int push_rt_task(struct rq *rq, bool pull)
 		return 0;
 
 retry:
+	/*
+	 * It's possible that the next_task slipped in of
+	 * higher priority than current. If that's the case
+	 * just reschedule current.
+	 */
+	if (unlikely(next_task->prio < rq->curr->prio)) {
+		resched_curr(rq);
+		return 0;
+	}
+
 	if (is_migration_disabled(next_task)) {
 		struct task_struct *push_task = NULL;
 		int cpu;
@@ -2030,6 +2028,18 @@ retry:
 		if (!pull || rq->push_busy)
 			return 0;
 
+		/*
+		 * Invoking find_lowest_rq() on anything but an RT task doesn't
+		 * make sense. Per the above priority check, curr has to
+		 * be of higher priority than next_task, so no need to
+		 * reschedule when bailing out.
+		 *
+		 * Note that the stoppers are masqueraded as SCHED_FIFO
+		 * (cf. sched_set_stop_task()), so we can't rely on rt_task().
+		 */
+		if (rq->curr->sched_class != &rt_sched_class)
+			return 0;
+
 		cpu = find_lowest_rq(rq->curr);
 		if (cpu == -1 || cpu == rq->cpu)
 			return 0;
@@ -2054,16 +2064,6 @@ retry:
 	if (WARN_ON(next_task == rq->curr))
 		return 0;
 
-	/*
-	 * It's possible that the next_task slipped in of
-	 * higher priority than current. If that's the case
-	 * just reschedule current.
-	 */
-	if (unlikely(next_task->prio < rq->curr->prio)) {
-		resched_curr(rq);
-		return 0;
-	}
-
 	/* We might release rq lock */
 	get_task_struct(next_task);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0d4217965561..58263f90c559 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -313,29 +313,6 @@ 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.
@@ -359,9 +336,8 @@ 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
 
@@ -2340,7 +2316,6 @@ 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 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);
@@ -2756,32 +2731,6 @@ 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;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index e8af72fd70bd..810750e62118 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -2290,7 +2290,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 
 			if (!(sd->flags & SD_SHARE_PKG_RESOURCES) && child &&
 			    (child->flags & SD_SHARE_PKG_RESOURCES)) {
-				struct sched_domain *top, *top_p;
+				struct sched_domain __rcu *top_p;
 				unsigned int nr_llcs;
 
 				/*
@@ -2315,11 +2315,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 				sd->imb_numa_nr = imb;
 
 				/* Set span based on the first NUMA domain. */
-				top = sd;
-				top_p = top->parent;
+				top_p = sd->parent;
 				while (top_p && !(top_p->flags & SD_NUMA)) {
-					top = top->parent;
-					top_p = top->parent;
+					top_p = top_p->parent;
 				}
 				imb_span = top_p ? top_p->span_weight : sd->span_weight;
 			} else {
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 22061d38fc00..19028e072cdb 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -415,7 +415,9 @@ free:
 
 static void
 ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
-			struct task_struct *prev, struct task_struct *next)
+				unsigned int prev_state,
+				struct task_struct *prev,
+				struct task_struct *next)
 {
 	unsigned long long timestamp;
 	int index;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f9feb197b2da..6762ae029fdd 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -7347,7 +7347,9 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
 
 static void
 ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,
-		    struct task_struct *prev, struct task_struct *next)
+				     unsigned int prev_state,
+				     struct task_struct *prev,
+				     struct task_struct *next)
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *pid_list;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 3147614c1812..2a19ea747ff4 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -759,7 +759,9 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable)
 
 static void
 event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
-		    struct task_struct *prev, struct task_struct *next)
+					unsigned int prev_state,
+					struct task_struct *prev,
+					struct task_struct *next)
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *no_pid_list;
@@ -783,7 +785,9 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
 
 static void
 event_filter_pid_sched_switch_probe_post(void *data, bool preempt,
-		    struct task_struct *prev, struct task_struct *next)
+					 unsigned int prev_state,
+					 struct task_struct *prev,
+					 struct task_struct *next)
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *no_pid_list;
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 870a08da5b48..1829b4cb8cc1 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1167,7 +1167,9 @@ thread_exit(struct osnoise_variables *osn_var, struct task_struct *t)
  * used to record the beginning and to report the end of a thread noise window.
  */
 static void
-trace_sched_switch_callback(void *data, bool preempt, struct task_struct *p,
+trace_sched_switch_callback(void *data, bool preempt,
+			    unsigned int prev_state,
+			    struct task_struct *p,
 			    struct task_struct *n)
 {
 	struct osnoise_variables *osn_var = this_cpu_osn_var();
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index e304196d7c28..993b0ed10d8c 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -22,6 +22,7 @@ static DEFINE_MUTEX(sched_register_mutex);
 
 static void
 probe_sched_switch(void *ignore, bool preempt,
+		   unsigned int prev_state,
 		   struct task_struct *prev, struct task_struct *next)
 {
 	int flags;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 2402de520eca..46429f9a96fa 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -426,6 +426,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 
 static void notrace
 probe_wakeup_sched_switch(void *ignore, bool preempt,
+			  unsigned int prev_state,
 			  struct task_struct *prev, struct task_struct *next)
 {
 	struct trace_array_cpu *data;
diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h
index 6a2a04d92f42..ca40a5258c87 100755
--- a/scripts/mkcompile_h
+++ b/scripts/mkcompile_h
@@ -5,9 +5,10 @@ TARGET=$1
 ARCH=$2
 SMP=$3
 PREEMPT=$4
-PREEMPT_RT=$5
-CC_VERSION="$6"
-LD=$7
+PREEMPT_DYNAMIC=$5
+PREEMPT_RT=$6
+CC_VERSION="$7"
+LD=$8
 
 # Do not expand names
 set -f
@@ -41,8 +42,14 @@ fi
 UTS_VERSION="#$VERSION"
 CONFIG_FLAGS=""
 if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi
-if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi
-if [ -n "$PREEMPT_RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT_RT"; fi
+
+if [ -n "$PREEMPT_RT" ] ; then
+	CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT_RT"
+elif [ -n "$PREEMPT_DYNAMIC" ] ; then
+	CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT_DYNAMIC"
+elif [ -n "$PREEMPT" ] ; then
+	CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"
+fi
 
 # Truncate to maximum length
 UTS_LEN=64