Merge tag 'sched-urgent-2020-11-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Thomas Gleixner:
 "A couple of scheduler fixes:

   - Make the conditional update of the overutilized state work
     correctly by caching the relevant flags state before overwriting
     them and checking them afterwards.

   - Fix a data race in the wakeup path which caused loadavg on ARM64
     platforms to become a random number generator.

   - Fix the ordering of the iowaiter accounting operations so it can't
     be decremented before it is incremented.

   - Fix a bug in the deadline scheduler vs. priority inheritance when a
     non-deadline task A has inherited the parameters of a deadline task
     B and then blocks on a non-deadline task C.

     The second inheritance step used the static deadline parameters of
     task A, which are usually 0, instead of further propagating task
     B's parameters. The zero initialized parameters trigger a bug in
     the deadline scheduler"

* tag 'sched-urgent-2020-11-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/deadline: Fix priority inheritance with multiple scheduling classes
  sched: Fix rq->nr_iowait ordering
  sched: Fix data-race in wakeup
  sched/fair: Fix overutilized update in enqueue_task_fair()

1 files changed, 24 insertions, 2 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 063cd120b459..76cd21fa5501 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -552,7 +552,6 @@ struct sched_dl_entity {
 	 * overruns.
 	 */
 	unsigned int			dl_throttled      : 1;
-	unsigned int			dl_boosted        : 1;
 	unsigned int			dl_yielded        : 1;
 	unsigned int			dl_non_contending : 1;
 	unsigned int			dl_overrun	  : 1;
@@ -571,6 +570,15 @@ struct sched_dl_entity {
 	 * time.
 	 */
 	struct hrtimer inactive_timer;
+
+#ifdef CONFIG_RT_MUTEXES
+	/*
+	 * Priority Inheritance. When a DEADLINE scheduling entity is boosted
+	 * pi_se points to the donor, otherwise points to the dl_se it belongs
+	 * to (the original one/itself).
+	 */
+	struct sched_dl_entity *pi_se;
+#endif
 };
 
 #ifdef CONFIG_UCLAMP_TASK
@@ -770,7 +778,6 @@ struct task_struct {
 	unsigned			sched_reset_on_fork:1;
 	unsigned			sched_contributes_to_load:1;
 	unsigned			sched_migrated:1;
-	unsigned			sched_remote_wakeup:1;
 #ifdef CONFIG_PSI
 	unsigned			sched_psi_wake_requeue:1;
 #endif
@@ -780,6 +787,21 @@ struct task_struct {
 
 	/* Unserialized, strictly 'current' */
 
+	/*
+	 * This field must not be in the scheduler word above due to wakelist
+	 * queueing no longer being serialized by p->on_cpu. However:
+	 *
+	 * p->XXX = X;			ttwu()
+	 * schedule()			  if (p->on_rq && ..) // false
+	 *   smp_mb__after_spinlock();	  if (smp_load_acquire(&p->on_cpu) && //true
+	 *   deactivate_task()		      ttwu_queue_wakelist())
+	 *     p->on_rq = 0;			p->sched_remote_wakeup = Y;
+	 *
+	 * guarantees all stores of 'current' are visible before
+	 * ->sched_remote_wakeup gets used, so it can be in this word.
+	 */
+	unsigned			sched_remote_wakeup:1;
+
 	/* Bit to tell LSMs we're in execve(): */
 	unsigned			in_execve:1;
 	unsigned			in_iowait:1;