Merge tag 'sched-core-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Core scheduler updates:

   - Add CONFIG_PREEMPT_DYNAMIC: this in its current form adds the
     preempt=none/voluntary/full boot options (default: full), to allow
     distros to build a PREEMPT kernel but fall back to close to
     PREEMPT_VOLUNTARY (or PREEMPT_NONE) runtime scheduling behavior via
     a boot time selection.

     There's also the /debug/sched_debug switch to do this runtime.

     This feature is implemented via runtime patching (a new variant of
     static calls).

     The scope of the runtime patching can be best reviewed by looking
     at the sched_dynamic_update() function in kernel/sched/core.c.

     ( Note that the dynamic none/voluntary mode isn't 100% identical,
       for example preempt-RCU is available in all cases, plus the
       preempt count is maintained in all models, which has runtime
       overhead even with the code patching. )

     The PREEMPT_VOLUNTARY/PREEMPT_NONE models, used by the vast
     majority of distributions, are supposed to be unaffected.

   - Fix ignored rescheduling after rcu_eqs_enter(). This is a bug that
     was found via rcutorture triggering a hang. The bug is that
     rcu_idle_enter() may wake up a NOCB kthread, but this happens after
     the last generic need_resched() check. Some cpuidle drivers fix it
     by chance but many others don't.

     In true 2020 fashion the original bug fix has grown into a 5-patch
     scheduler/RCU fix series plus another 16 RCU patches to address the
     underlying issue of missed preemption events. These are the initial
     fixes that should fix current incarnations of the bug.

   - Clean up rbtree usage in the scheduler, by providing & using the
     following consistent set of rbtree APIs:

       partial-order; less() based:
         - rb_add(): add a new entry to the rbtree
         - rb_add_cached(): like rb_add(), but for a rb_root_cached

       total-order; cmp() based:
         - rb_find(): find an entry in an rbtree
         - rb_find_add(): find an entry, and add if not found

         - rb_find_first(): find the first (leftmost) matching entry
         - rb_next_match(): continue from rb_find_first()
         - rb_for_each(): iterate a sub-tree using the previous two

   - Improve the SMP/NUMA load-balancer: scan for an idle sibling in a
     single pass. This is a 4-commit series where each commit improves
     one aspect of the idle sibling scan logic.

   - Improve the cpufreq cooling driver by getting the effective CPU
     utilization metrics from the scheduler

   - Improve the fair scheduler's active load-balancing logic by
     reducing the number of active LB attempts & lengthen the
     load-balancing interval. This improves stress-ng mmapfork
     performance.

   - Fix CFS's estimated utilization (util_est) calculation bug that can
     result in too high utilization values

  Misc updates & fixes:

   - Fix the HRTICK reprogramming & optimization feature

   - Fix SCHED_SOFTIRQ raising race & warning in the CPU offlining code

   - Reduce dl_add_task_root_domain() overhead

   - Fix uprobes refcount bug

   - Process pending softirqs in flush_smp_call_function_from_idle()

   - Clean up task priority related defines, remove *USER_*PRIO and
     USER_PRIO()

   - Simplify the sched_init_numa() deduplication sort

   - Documentation updates

   - Fix EAS bug in update_misfit_status(), which degraded the quality
     of energy-balancing

   - Smaller cleanups"

* tag 'sched-core-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (51 commits)
  sched,x86: Allow !PREEMPT_DYNAMIC
  entry/kvm: Explicitly flush pending rcuog wakeup before last rescheduling point
  entry: Explicitly flush pending rcuog wakeup before last rescheduling point
  rcu/nocb: Trigger self-IPI on late deferred wake up before user resume
  rcu/nocb: Perform deferred wake up before last idle's need_resched() check
  rcu: Pull deferred rcuog wake up to rcu_eqs_enter() callers
  sched/features: Distinguish between NORMAL and DEADLINE hrtick
  sched/features: Fix hrtick reprogramming
  sched/deadline: Reduce rq lock contention in dl_add_task_root_domain()
  uprobes: (Re)add missing get_uprobe() in __find_uprobe()
  smp: Process pending softirqs in flush_smp_call_function_from_idle()
  sched: Harden PREEMPT_DYNAMIC
  static_call: Allow module use without exposing static_call_key
  sched: Add /debug/sched_preempt
  preempt/dynamic: Support dynamic preempt with preempt= boot option
  preempt/dynamic: Provide irqentry_exit_cond_resched() static call
  preempt/dynamic: Provide preempt_schedule[_notrace]() static calls
  preempt/dynamic: Provide cond_resched() and might_resched() static calls
  preempt: Introduce CONFIG_PREEMPT_DYNAMIC
  static_call: Provide DEFINE_STATIC_CALL_RET0()
  ...

2 files changed, 129 insertions, 146 deletions

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;
 }
 
 /*