20 files changed, 941 insertions, 612 deletions

diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index bf82259cff96..416017301660 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -40,6 +40,7 @@ config PREEMPT
 	depends on !ARCH_NO_PREEMPT
 	select PREEMPTION
 	select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
+	select PREEMPT_DYNAMIC if HAVE_PREEMPT_DYNAMIC
 	help
 	  This option reduces the latency of the kernel by making
 	  all kernel code (that is not executing in a critical section)
@@ -80,3 +81,21 @@ config PREEMPT_COUNT
 config PREEMPTION
        bool
        select PREEMPT_COUNT
+
+config PREEMPT_DYNAMIC
+	bool
+	help
+	  This option allows to define the preemption model on the kernel
+	  command line parameter and thus override the default preemption
+	  model defined during compile time.
+
+	  The feature is primarily interesting for Linux distributions which
+	  provide a pre-built kernel binary to reduce the number of kernel
+	  flavors they offer while still offering different usecases.
+
+	  The runtime overhead is negligible with HAVE_STATIC_CALL_INLINE enabled
+	  but if runtime patching is not available for the specific architecture
+	  then the potential overhead should be considered.
+
+	  Interesting if you want the same pre-built kernel should be used for
+	  both Server and Desktop workloads.
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index f9d491b17b78..8442e5c9cfa2 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -184,6 +184,10 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 		 * enabled above.
 		 */
 		local_irq_disable_exit_to_user();
+
+		/* Check if any of the above work has queued a deferred wakeup */
+		rcu_nocb_flush_deferred_wakeup();
+
 		ti_work = READ_ONCE(current_thread_info()->flags);
 	}
 
@@ -197,6 +201,9 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
 
 	lockdep_assert_irqs_disabled();
 
+	/* Flush pending rcuog wakeup before the last need_resched() check */
+	rcu_nocb_flush_deferred_wakeup();
+
 	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
 		ti_work = exit_to_user_mode_loop(regs, ti_work);
 
@@ -385,6 +392,9 @@ void irqentry_exit_cond_resched(void)
 			preempt_schedule_irq();
 	}
 }
+#ifdef CONFIG_PREEMPT_DYNAMIC
+DEFINE_STATIC_CALL(irqentry_exit_cond_resched, irqentry_exit_cond_resched);
+#endif
 
 noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 {
@@ -411,8 +421,13 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 		}
 
 		instrumentation_begin();
-		if (IS_ENABLED(CONFIG_PREEMPTION))
+		if (IS_ENABLED(CONFIG_PREEMPTION)) {
+#ifdef CONFIG_PREEMT_DYNAMIC
+			static_call(irqentry_exit_cond_resched)();
+#else
 			irqentry_exit_cond_resched();
+#endif
+		}
 		/* Covers both tracing and lockdep */
 		trace_hardirqs_on();
 		instrumentation_end();
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c37401e3e5f7..5fe7d6346762 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1597,50 +1597,91 @@ static void perf_event_groups_init(struct perf_event_groups *groups)
 	groups->index = 0;
 }
 
+static inline struct cgroup *event_cgroup(const struct perf_event *event)
+{
+	struct cgroup *cgroup = NULL;
+
+#ifdef CONFIG_CGROUP_PERF
+	if (event->cgrp)
+		cgroup = event->cgrp->css.cgroup;
+#endif
+
+	return cgroup;
+}
+
 /*
  * Compare function for event groups;
  *
  * Implements complex key that first sorts by CPU and then by virtual index
  * which provides ordering when rotating groups for the same CPU.
  */
-static bool
-perf_event_groups_less(struct perf_event *left, struct perf_event *right)
+static __always_inline int
+perf_event_groups_cmp(const int left_cpu, const struct cgroup *left_cgroup,
+		      const u64 left_group_index, const struct perf_event *right)
 {
-	if (left->cpu < right->cpu)
-		return true;
-	if (left->cpu > right->cpu)
-		return false;
+	if (left_cpu < right->cpu)
+		return -1;
+	if (left_cpu > right->cpu)
+		return 1;
 
 #ifdef CONFIG_CGROUP_PERF
-	if (left->cgrp != right->cgrp) {
-		if (!left->cgrp || !left->cgrp->css.cgroup) {
-			/*
-			 * Left has no cgroup but right does, no cgroups come
-			 * first.
-			 */
-			return true;
-		}
-		if (!right->cgrp || !right->cgrp->css.cgroup) {
-			/*
-			 * Right has no cgroup but left does, no cgroups come
-			 * first.
-			 */
-			return false;
-		}
-		/* Two dissimilar cgroups, order by id. */
-		if (left->cgrp->css.cgroup->kn->id < right->cgrp->css.cgroup->kn->id)
-			return true;
+	{
+		const struct cgroup *right_cgroup = event_cgroup(right);
 
-		return false;
+		if (left_cgroup != right_cgroup) {
+			if (!left_cgroup) {
+				/*
+				 * Left has no cgroup but right does, no
+				 * cgroups come first.
+				 */
+				return -1;
+			}
+			if (!right_cgroup) {
+				/*
+				 * Right has no cgroup but left does, no
+				 * cgroups come first.
+				 */
+				return 1;
+			}
+			/* Two dissimilar cgroups, order by id. */
+			if (cgroup_id(left_cgroup) < cgroup_id(right_cgroup))
+				return -1;
+
+			return 1;
+		}
 	}
 #endif
 
-	if (left->group_index < right->group_index)
-		return true;
-	if (left->group_index > right->group_index)
-		return false;
+	if (left_group_index < right->group_index)
+		return -1;
+	if (left_group_index > right->group_index)
+		return 1;
 
-	return false;
+	return 0;
+}
+
+#define __node_2_pe(node) \
+	rb_entry((node), struct perf_event, group_node)
+
+static inline bool __group_less(struct rb_node *a, const struct rb_node *b)
+{
+	struct perf_event *e = __node_2_pe(a);
+	return perf_event_groups_cmp(e->cpu, event_cgroup(e), e->group_index,
+				     __node_2_pe(b)) < 0;
+}
+
+struct __group_key {
+	int cpu;
+	struct cgroup *cgroup;
+};
+
+static inline int __group_cmp(const void *key, const struct rb_node *node)
+{
+	const struct __group_key *a = key;
+	const struct perf_event *b = __node_2_pe(node);
+
+	/* partial/subtree match: @cpu, @cgroup; ignore: @group_index */
+	return perf_event_groups_cmp(a->cpu, a->cgroup, b->group_index, b);
 }
 
 /*
@@ -1652,27 +1693,9 @@ static void
 perf_event_groups_insert(struct perf_event_groups *groups,
 			 struct perf_event *event)
 {
-	struct perf_event *node_event;
-	struct rb_node *parent;
-	struct rb_node **node;
-
 	event->group_index = ++groups->index;
 
-	node = &groups->tree.rb_node;
-	parent = *node;
-
-	while (*node) {
-		parent = *node;
-		node_event = container_of(*node, struct perf_event, group_node);
-
-		if (perf_event_groups_less(event, node_event))
-			node = &parent->rb_left;
-		else
-			node = &parent->rb_right;
-	}
-
-	rb_link_node(&event->group_node, parent, node);
-	rb_insert_color(&event->group_node, &groups->tree);
+	rb_add(&event->group_node, &groups->tree, __group_less);
 }
 
 /*
@@ -1720,45 +1743,17 @@ static struct perf_event *
 perf_event_groups_first(struct perf_event_groups *groups, int cpu,
 			struct cgroup *cgrp)
 {
-	struct perf_event *node_event = NULL, *match = NULL;
-	struct rb_node *node = groups->tree.rb_node;
-#ifdef CONFIG_CGROUP_PERF
-	u64 node_cgrp_id, cgrp_id = 0;
-
-	if (cgrp)
-		cgrp_id = cgrp->kn->id;
-#endif
-
-	while (node) {
-		node_event = container_of(node, struct perf_event, group_node);
-
-		if (cpu < node_event->cpu) {
-			node = node->rb_left;
-			continue;
-		}
-		if (cpu > node_event->cpu) {
-			node = node->rb_right;
-			continue;
-		}
-#ifdef CONFIG_CGROUP_PERF
-		node_cgrp_id = 0;
-		if (node_event->cgrp && node_event->cgrp->css.cgroup)
-			node_cgrp_id = node_event->cgrp->css.cgroup->kn->id;
+	struct __group_key key = {
+		.cpu = cpu,
+		.cgroup = cgrp,
+	};
+	struct rb_node *node;
 
-		if (cgrp_id < node_cgrp_id) {
-			node = node->rb_left;
-			continue;
-		}
-		if (cgrp_id > node_cgrp_id) {
-			node = node->rb_right;
-			continue;
-		}
-#endif
-		match = node_event;
-		node = node->rb_left;
-	}
+	node = rb_find_first(&key, &groups->tree, __group_cmp);
+	if (node)
+		return __node_2_pe(node);
 
-	return match;
+	return NULL;
 }
 
 /*
@@ -1767,27 +1762,17 @@ perf_event_groups_first(struct perf_event_groups *groups, int cpu,
 static struct perf_event *
 perf_event_groups_next(struct perf_event *event)
 {
-	struct perf_event *next;
-#ifdef CONFIG_CGROUP_PERF
-	u64 curr_cgrp_id = 0;
-	u64 next_cgrp_id = 0;
-#endif
-
-	next = rb_entry_safe(rb_next(&event->group_node), typeof(*event), group_node);
-	if (next == NULL || next->cpu != event->cpu)
-		return NULL;
-
-#ifdef CONFIG_CGROUP_PERF
-	if (event->cgrp && event->cgrp->css.cgroup)
-		curr_cgrp_id = event->cgrp->css.cgroup->kn->id;
+	struct __group_key key = {
+		.cpu = event->cpu,
+		.cgroup = event_cgroup(event),
+	};
+	struct rb_node *next;
 
-	if (next->cgrp && next->cgrp->css.cgroup)
-		next_cgrp_id = next->cgrp->css.cgroup->kn->id;
+	next = rb_next_match(&key, &event->group_node, __group_cmp);
+	if (next)
+		return __node_2_pe(next);
 
-	if (curr_cgrp_id != next_cgrp_id)
-		return NULL;
-#endif
-	return next;
+	return NULL;
 }
 
 /*
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index bf9edd8d75be..3ea7f8f92f1d 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -613,41 +613,56 @@ static void put_uprobe(struct uprobe *uprobe)
 	}
 }
 
-static int match_uprobe(struct uprobe *l, struct uprobe *r)
+static __always_inline
+int uprobe_cmp(const struct inode *l_inode, const loff_t l_offset,
+	       const struct uprobe *r)
 {
-	if (l->inode < r->inode)
+	if (l_inode < r->inode)
 		return -1;
 
-	if (l->inode > r->inode)
+	if (l_inode > r->inode)
 		return 1;
 
-	if (l->offset < r->offset)
+	if (l_offset < r->offset)
 		return -1;
 
-	if (l->offset > r->offset)
+	if (l_offset > r->offset)
 		return 1;
 
 	return 0;
 }
 
+#define __node_2_uprobe(node) \
+	rb_entry((node), struct uprobe, rb_node)
+
+struct __uprobe_key {
+	struct inode *inode;
+	loff_t offset;
+};
+
+static inline int __uprobe_cmp_key(const void *key, const struct rb_node *b)
+{
+	const struct __uprobe_key *a = key;
+	return uprobe_cmp(a->inode, a->offset, __node_2_uprobe(b));
+}
+
+static inline int __uprobe_cmp(struct rb_node *a, const struct rb_node *b)
+{
+	struct uprobe *u = __node_2_uprobe(a);
+	return uprobe_cmp(u->inode, u->offset, __node_2_uprobe(b));
+}
+
 static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset)
 {
-	struct uprobe u = { .inode = inode, .offset = offset };
-	struct rb_node *n = uprobes_tree.rb_node;
-	struct uprobe *uprobe;
-	int match;
+	struct __uprobe_key key = {
+		.inode = inode,
+		.offset = offset,
+	};
+	struct rb_node *node = rb_find(&key, &uprobes_tree, __uprobe_cmp_key);
 
-	while (n) {
-		uprobe = rb_entry(n, struct uprobe, rb_node);
-		match = match_uprobe(&u, uprobe);
-		if (!match)
-			return get_uprobe(uprobe);
+	if (node)
+		return get_uprobe(__node_2_uprobe(node));
 
-		if (match < 0)
-			n = n->rb_left;
-		else
-			n = n->rb_right;
-	}
 	return NULL;
 }
 
@@ -668,32 +683,15 @@ static struct uprobe *find_uprobe(struct inode *inode, loff_t offset)
 
 static struct uprobe *__insert_uprobe(struct uprobe *uprobe)
 {
-	struct rb_node **p = &uprobes_tree.rb_node;
-	struct rb_node *parent = NULL;
-	struct uprobe *u;
-	int match;
+	struct rb_node *node;
 
-	while (*p) {
-		parent = *p;
-		u = rb_entry(parent, struct uprobe, rb_node);
-		match = match_uprobe(uprobe, u);
-		if (!match)
-			return get_uprobe(u);
+	node = rb_find_add(&uprobe->rb_node, &uprobes_tree, __uprobe_cmp);
+	if (node)
+		return get_uprobe(__node_2_uprobe(node));
 
-		if (match < 0)
-			p = &parent->rb_left;
-		else
-			p = &parent->rb_right;
-
-	}
-
-	u = NULL;
-	rb_link_node(&uprobe->rb_node, parent, p);
-	rb_insert_color(&uprobe->rb_node, &uprobes_tree);
 	/* get access + creation ref */
 	refcount_set(&uprobe->ref, 2);
-
-	return u;
+	return NULL;
 }
 
 /*
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 47a6e0b8073d..03b21135313c 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -267,27 +267,18 @@ rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
 	return 1;
 }
 
+#define __node_2_waiter(node) \
+	rb_entry((node), struct rt_mutex_waiter, tree_entry)
+
+static inline bool __waiter_less(struct rb_node *a, const struct rb_node *b)
+{
+	return rt_mutex_waiter_less(__node_2_waiter(a), __node_2_waiter(b));
+}
+
 static void
 rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
 {
-	struct rb_node **link = &lock->waiters.rb_root.rb_node;
-	struct rb_node *parent = NULL;
-	struct rt_mutex_waiter *entry;
-	bool leftmost = true;
-
-	while (*link) {
-		parent = *link;
-		entry = rb_entry(parent, struct rt_mutex_waiter, tree_entry);
-		if (rt_mutex_waiter_less(waiter, entry)) {
-			link = &parent->rb_left;
-		} else {
-			link = &parent->rb_right;
-			leftmost = false;
-		}
-	}
-
-	rb_link_node(&waiter->tree_entry, parent, link);
-	rb_insert_color_cached(&waiter->tree_entry, &lock->waiters, leftmost);
+	rb_add_cached(&waiter->tree_entry, &lock->waiters, __waiter_less);
 }
 
 static void
@@ -300,27 +291,18 @@ rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
 	RB_CLEAR_NODE(&waiter->tree_entry);
 }
 
+#define __node_2_pi_waiter(node) \
+	rb_entry((node), struct rt_mutex_waiter, pi_tree_entry)
+
+static inline bool __pi_waiter_less(struct rb_node *a, const struct rb_node *b)
+{
+	return rt_mutex_waiter_less(__node_2_pi_waiter(a), __node_2_pi_waiter(b));
+}
+
 static void
 rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
 {
-	struct rb_node **link = &task->pi_waiters.rb_root.rb_node;
-	struct rb_node *parent = NULL;
-	struct rt_mutex_waiter *entry;
-	bool leftmost = true;
-
-	while (*link) {
-		parent = *link;
-		entry = rb_entry(parent, struct rt_mutex_waiter, pi_tree_entry);
-		if (rt_mutex_waiter_less(waiter, entry)) {
-			link = &parent->rb_left;
-		} else {
-			link = &parent->rb_right;
-			leftmost = false;
-		}
-	}
-
-	rb_link_node(&waiter->pi_tree_entry, parent, link);
-	rb_insert_color_cached(&waiter->pi_tree_entry, &task->pi_waiters, leftmost);
+	rb_add_cached(&waiter->pi_tree_entry, &task->pi_waiters, __pi_waiter_less);
 }
 
 static void
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 0f4a6a3c057b..da6f5213fb74 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -649,7 +649,6 @@ static noinstr void rcu_eqs_enter(bool user)
 	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	rdp = this_cpu_ptr(&rcu_data);
-	do_nocb_deferred_wakeup(rdp);
 	rcu_prepare_for_idle();
 	rcu_preempt_deferred_qs(current);
 
@@ -683,6 +682,50 @@ void rcu_idle_enter(void)
 EXPORT_SYMBOL_GPL(rcu_idle_enter);
 
 #ifdef CONFIG_NO_HZ_FULL
+
+#if !defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)
+/*
+ * An empty function that will trigger a reschedule on
+ * IRQ tail once IRQs get re-enabled on userspace/guest resume.
+ */
+static void late_wakeup_func(struct irq_work *work)
+{
+}
+
+static DEFINE_PER_CPU(struct irq_work, late_wakeup_work) =
+	IRQ_WORK_INIT(late_wakeup_func);
+
+/*
+ * If either:
+ *
+ * 1) the task is about to enter in guest mode and $ARCH doesn't support KVM generic work
+ * 2) the task is about to enter in user mode and $ARCH doesn't support generic entry.
+ *
+ * In these cases the late RCU wake ups aren't supported in the resched loops and our
+ * last resort is to fire a local irq_work that will trigger a reschedule once IRQs
+ * get re-enabled again.
+ */
+noinstr static void rcu_irq_work_resched(void)
+{
+	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+
+	if (IS_ENABLED(CONFIG_GENERIC_ENTRY) && !(current->flags & PF_VCPU))
+		return;
+
+	if (IS_ENABLED(CONFIG_KVM_XFER_TO_GUEST_WORK) && (current->flags & PF_VCPU))
+		return;
+
+	instrumentation_begin();
+	if (do_nocb_deferred_wakeup(rdp) && need_resched()) {
+		irq_work_queue(this_cpu_ptr(&late_wakeup_work));
+	}
+	instrumentation_end();
+}
+
+#else
+static inline void rcu_irq_work_resched(void) { }
+#endif
+
 /**
  * rcu_user_enter - inform RCU that we are resuming userspace.
  *
@@ -697,8 +740,16 @@ EXPORT_SYMBOL_GPL(rcu_idle_enter);
 noinstr void rcu_user_enter(void)
 {
 	lockdep_assert_irqs_disabled();
+
+	/*
+	 * Other than generic entry implementation, we may be past the last
+	 * rescheduling opportunity in the entry code. Trigger a self IPI
+	 * that will fire and reschedule once we resume in user/guest mode.
+	 */
+	rcu_irq_work_resched();
 	rcu_eqs_enter(true);
 }
+
 #endif /* CONFIG_NO_HZ_FULL */
 
 /**
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 5d359b9f9fec..71821d59d95c 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -435,7 +435,7 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty,
 				 unsigned long flags);
 static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
-static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
+static bool do_nocb_deferred_wakeup(struct rcu_data *rdp);
 static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
 static void rcu_spawn_cpu_nocb_kthread(int cpu);
 static void __init rcu_spawn_nocb_kthreads(void);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 231a0c6cf03c..2d603771c7dc 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1632,8 +1632,8 @@ bool rcu_is_nocb_cpu(int cpu)
  * Kick the GP kthread for this NOCB group.  Caller holds ->nocb_lock
  * and this function releases it.
  */
-static void wake_nocb_gp(struct rcu_data *rdp, bool force,
-			   unsigned long flags)
+static bool wake_nocb_gp(struct rcu_data *rdp, bool force,
+			 unsigned long flags)
 	__releases(rdp->nocb_lock)
 {
 	bool needwake = false;
@@ -1644,7 +1644,7 @@ static void wake_nocb_gp(struct rcu_data *rdp, bool force,
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 				    TPS("AlreadyAwake"));
 		rcu_nocb_unlock_irqrestore(rdp, flags);
-		return;
+		return false;
 	}
 	del_timer(&rdp->nocb_timer);
 	rcu_nocb_unlock_irqrestore(rdp, flags);
@@ -1657,6 +1657,8 @@ static void wake_nocb_gp(struct rcu_data *rdp, bool force,
 	raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags);
 	if (needwake)
 		wake_up_process(rdp_gp->nocb_gp_kthread);
+
+	return needwake;
 }
 
 /*
@@ -2251,20 +2253,23 @@ static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
 }
 
 /* Do a deferred wakeup of rcu_nocb_kthread(). */
-static void do_nocb_deferred_wakeup_common(struct rcu_data *rdp)
+static bool do_nocb_deferred_wakeup_common(struct rcu_data *rdp)
 {
 	unsigned long flags;
 	int ndw;
+	int ret;
 
 	rcu_nocb_lock_irqsave(rdp, flags);
 	if (!rcu_nocb_need_deferred_wakeup(rdp)) {
 		rcu_nocb_unlock_irqrestore(rdp, flags);
-		return;
+		return false;
 	}
 	ndw = READ_ONCE(rdp->nocb_defer_wakeup);
 	WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
-	wake_nocb_gp(rdp, ndw == RCU_NOCB_WAKE_FORCE, flags);
+	ret = wake_nocb_gp(rdp, ndw == RCU_NOCB_WAKE_FORCE, flags);
 	trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DeferredWake"));
+
+	return ret;
 }
 
 /* Do a deferred wakeup of rcu_nocb_kthread() from a timer handler. */
@@ -2280,11 +2285,18 @@ static void do_nocb_deferred_wakeup_timer(struct timer_list *t)
  * This means we do an inexact common-case check.  Note that if
  * we miss, ->nocb_timer will eventually clean things up.
  */
-static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+static bool do_nocb_deferred_wakeup(struct rcu_data *rdp)
 {
 	if (rcu_nocb_need_deferred_wakeup(rdp))
-		do_nocb_deferred_wakeup_common(rdp);
+		return do_nocb_deferred_wakeup_common(rdp);
+	return false;
+}
+
+void rcu_nocb_flush_deferred_wakeup(void)
+{
+	do_nocb_deferred_wakeup(this_cpu_ptr(&rcu_data));
 }
+EXPORT_SYMBOL_GPL(rcu_nocb_flush_deferred_wakeup);
 
 static int rdp_offload_toggle(struct rcu_data *rdp,
 			       bool offload, unsigned long flags)
@@ -2835,8 +2847,9 @@ static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
 	return false;
 }
 
-static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+static bool do_nocb_deferred_wakeup(struct rcu_data *rdp)
 {
+	return false;
 }
 
 static void rcu_spawn_cpu_nocb_kthread(int cpu)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 22f6748c16f6..7f5ffc878411 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -355,8 +355,9 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
 static void __hrtick_restart(struct rq *rq)
 {
 	struct hrtimer *timer = &rq->hrtick_timer;
+	ktime_t time = rq->hrtick_time;
 
-	hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED_HARD);
+	hrtimer_start(timer, time, HRTIMER_MODE_ABS_PINNED_HARD);
 }
 
 /*
@@ -380,7 +381,6 @@ static void __hrtick_start(void *arg)
 void hrtick_start(struct rq *rq, u64 delay)
 {
 	struct hrtimer *timer = &rq->hrtick_timer;
-	ktime_t time;
 	s64 delta;
 
 	/*
@@ -388,9 +388,7 @@ void hrtick_start(struct rq *rq, u64 delay)
 	 * doesn't make sense and can cause timer DoS.
 	 */
 	delta = max_t(s64, delay, 10000LL);
-	time = ktime_add_ns(timer->base->get_time(), delta);
-
-	hrtimer_set_expires(timer, time);
+	rq->hrtick_time = ktime_add_ns(timer->base->get_time(), delta);
 
 	if (rq == this_rq())
 		__hrtick_restart(rq);
@@ -4970,7 +4968,7 @@ static void __sched notrace __schedule(bool preempt)
 
 	schedule_debug(prev, preempt);
 
-	if (sched_feat(HRTICK))
+	if (sched_feat(HRTICK) || sched_feat(HRTICK_DL))
 		hrtick_clear(rq);
 
 	local_irq_disable();
@@ -5264,6 +5262,12 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
 NOKPROBE_SYMBOL(preempt_schedule);
 EXPORT_SYMBOL(preempt_schedule);
 
+#ifdef CONFIG_PREEMPT_DYNAMIC
+DEFINE_STATIC_CALL(preempt_schedule, __preempt_schedule_func);
+EXPORT_STATIC_CALL_TRAMP(preempt_schedule);
+#endif
+
+
 /**
  * preempt_schedule_notrace - preempt_schedule called by tracing
  *
@@ -5316,8 +5320,197 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
 }
 EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
 
+#ifdef CONFIG_PREEMPT_DYNAMIC
+DEFINE_STATIC_CALL(preempt_schedule_notrace, __preempt_schedule_notrace_func);
+EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
+#endif
+
 #endif /* CONFIG_PREEMPTION */
 
+#ifdef CONFIG_PREEMPT_DYNAMIC
+
+#include <linux/entry-common.h>
+
+/*
+ * SC:cond_resched
+ * SC:might_resched
+ * SC:preempt_schedule
+ * SC:preempt_schedule_notrace
+ * SC:irqentry_exit_cond_resched
+ *
+ *
+ * NONE:
+ *   cond_resched               <- __cond_resched
+ *   might_resched              <- RET0
+ *   preempt_schedule           <- NOP
+ *   preempt_schedule_notrace   <- NOP
+ *   irqentry_exit_cond_resched <- NOP
+ *
+ * VOLUNTARY:
+ *   cond_resched               <- __cond_resched
+ *   might_resched              <- __cond_resched
+ *   preempt_schedule           <- NOP
+ *   preempt_schedule_notrace   <- NOP
+ *   irqentry_exit_cond_resched <- NOP
+ *
+ * FULL:
+ *   cond_resched               <- RET0
+ *   might_resched              <- RET0
+ *   preempt_schedule           <- preempt_schedule
+ *   preempt_schedule_notrace   <- preempt_schedule_notrace
+ *   irqentry_exit_cond_resched <- irqentry_exit_cond_resched
+ */
+
+enum {
+	preempt_dynamic_none = 0,
+	preempt_dynamic_voluntary,
+	preempt_dynamic_full,
+};
+
+static int preempt_dynamic_mode = preempt_dynamic_full;
+
+static int sched_dynamic_mode(const char *str)
+{
+	if (!strcmp(str, "none"))
+		return 0;
+
+	if (!strcmp(str, "voluntary"))
+		return 1;
+
+	if (!strcmp(str, "full"))
+		return 2;
+
+	return -1;
+}
+
+static void sched_dynamic_update(int mode)
+{
+	/*
+	 * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
+	 * the ZERO state, which is invalid.
+	 */
+	static_call_update(cond_resched, __cond_resched);
+	static_call_update(might_resched, __cond_resched);
+	static_call_update(preempt_schedule, __preempt_schedule_func);
+	static_call_update(preempt_schedule_notrace, __preempt_schedule_notrace_func);
+	static_call_update(irqentry_exit_cond_resched, irqentry_exit_cond_resched);
+
+	switch (mode) {
+	case preempt_dynamic_none:
+		static_call_update(cond_resched, __cond_resched);
+		static_call_update(might_resched, (typeof(&__cond_resched)) __static_call_return0);
+		static_call_update(preempt_schedule, (typeof(&preempt_schedule)) NULL);
+		static_call_update(preempt_schedule_notrace, (typeof(&preempt_schedule_notrace)) NULL);
+		static_call_update(irqentry_exit_cond_resched, (typeof(&irqentry_exit_cond_resched)) NULL);
+		pr_info("Dynamic Preempt: none\n");
+		break;
+
+	case preempt_dynamic_voluntary:
+		static_call_update(cond_resched, __cond_resched);
+		static_call_update(might_resched, __cond_resched);
+		static_call_update(preempt_schedule, (typeof(&preempt_schedule)) NULL);
+		static_call_update(preempt_schedule_notrace, (typeof(&preempt_schedule_notrace)) NULL);
+		static_call_update(irqentry_exit_cond_resched, (typeof(&irqentry_exit_cond_resched)) NULL);
+		pr_info("Dynamic Preempt: voluntary\n");
+		break;
+
+	case preempt_dynamic_full:
+		static_call_update(cond_resched, (typeof(&__cond_resched)) __static_call_return0);
+		static_call_update(might_resched, (typeof(&__cond_resched)) __static_call_return0);
+		static_call_update(preempt_schedule, __preempt_schedule_func);
+		static_call_update(preempt_schedule_notrace, __preempt_schedule_notrace_func);
+		static_call_update(irqentry_exit_cond_resched, irqentry_exit_cond_resched);
+		pr_info("Dynamic Preempt: full\n");
+		break;
+	}
+
+	preempt_dynamic_mode = mode;
+}
+
+static int __init setup_preempt_mode(char *str)
+{
+	int mode = sched_dynamic_mode(str);
+	if (mode < 0) {
+		pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
+		return 1;
+	}
+
+	sched_dynamic_update(mode);
+	return 0;
+}
+__setup("preempt=", setup_preempt_mode);
+
+#ifdef CONFIG_SCHED_DEBUG
+
+static ssize_t sched_dynamic_write(struct file *filp, const char __user *ubuf,
+				   size_t cnt, loff_t *ppos)
+{
+	char buf[16];
+	int mode;
+
+	if (cnt > 15)
+		cnt = 15;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+	mode = sched_dynamic_mode(strstrip(buf));
+	if (mode < 0)
+		return mode;
+
+	sched_dynamic_update(mode);
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
+static int sched_dynamic_show(struct seq_file *m, void *v)
+{
+	static const char * preempt_modes[] = {
+		"none", "voluntary", "full"
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(preempt_modes); i++) {
+		if (preempt_dynamic_mode == i)
+			seq_puts(m, "(");