Merge tag 'sched-urgent-2021-06-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:
 "Misc fixes:

   - Fix performance regression caused by lack of intended batching of
     RCU callbacks by over-eager NOHZ-full code.

   - Fix cgroups related corruption of load_avg and load_sum metrics.

   - Three fixes to fix blocked load, util_sum/runnable_sum and util_est
     tracking bugs"

* tag 'sched-urgent-2021-06-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Fix util_est UTIL_AVG_UNCHANGED handling
  sched/pelt: Ensure that *_sum is always synced with *_avg
  tick/nohz: Only check for RCU deferred wakeup on user/guest entry when needed
  sched/fair: Make sure to update tg contrib for blocked load
  sched/fair: Keep load_avg and load_sum synced

3 files changed, 17 insertions, 1 deletions

diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h
index 8b2b1d68b954..136b8d97d8c0 100644
--- a/include/linux/entry-kvm.h
+++ b/include/linux/entry-kvm.h
@@ -3,6 +3,7 @@
 #define __LINUX_ENTRYKVM_H
 
 #include <linux/entry-common.h>
+#include <linux/tick.h>
 
 /* Transfer to guest mode work */
 #ifdef CONFIG_KVM_XFER_TO_GUEST_WORK
@@ -57,7 +58,7 @@ int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu);
 static inline void xfer_to_guest_mode_prepare(void)
 {
 	lockdep_assert_irqs_disabled();
-	rcu_nocb_flush_deferred_wakeup();
+	tick_nohz_user_enter_prepare();
 }
 
 /**
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d2c881384517..28a98fc4ded4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -350,11 +350,19 @@ struct load_weight {
  * Only for tasks we track a moving average of the past instantaneous
  * estimated utilization. This allows to absorb sporadic drops in utilization
  * of an otherwise almost periodic task.
+ *
+ * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg
+ * updates. When a task is dequeued, its util_est should not be updated if its
+ * util_avg has not been updated in the meantime.
+ * This information is mapped into the MSB bit of util_est.enqueued at dequeue
+ * time. Since max value of util_est.enqueued for a task is 1024 (PELT util_avg
+ * for a task) it is safe to use MSB.
  */
 struct util_est {
 	unsigned int			enqueued;
 	unsigned int			ewma;
 #define UTIL_EST_WEIGHT_SHIFT		2
+#define UTIL_AVG_UNCHANGED		0x80000000
 } __attribute__((__aligned__(sizeof(u64))));
 
 /*
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 7340613c7eff..1a0ff88fa107 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -11,6 +11,7 @@
 #include <linux/context_tracking_state.h>
 #include <linux/cpumask.h>
 #include <linux/sched.h>
+#include <linux/rcupdate.h>
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 extern void __init tick_init(void);
@@ -300,4 +301,10 @@ static inline void tick_nohz_task_switch(void)
 		__tick_nohz_task_switch();
 }
 
+static inline void tick_nohz_user_enter_prepare(void)
+{
+	if (tick_nohz_full_cpu(smp_processor_id()))
+		rcu_nocb_flush_deferred_wakeup();
+}
+
 #endif