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()
  ...

3 files changed, 75 insertions, 11 deletions

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)