sched: Optimize finish_lock_switch()

The kernel test robot measured a -1.6% performance regression on
will-it-scale/sched_yield due to commit:

  2558aacf ("sched/hotplug: Ensure only per-cpu kthreads run during hotplug")

Even though we were careful to replace a single load with another
single load from the same cacheline.

Restore finish_lock_switch() to the exact state before the offending
patch and solve the problem differently.

Fixes: 2558aacf ("sched/hotplug: Ensure only per-cpu kthreads run during hotplug")
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201210161408.GX3021@hirez.programming.kicks-ass.net

kernel/sched/core.c

@@ -3985,15 +3985,20 @@ static void do_balance_callbacks(struct rq *rq, struct callback_head *head)
 	}
 }
 
+static void balance_push(struct rq *rq);
+
+struct callback_head balance_push_callback = {
+	.next = NULL,
+	.func = (void (*)(struct callback_head *))balance_push,
+};
+
 static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
 {
 	struct callback_head *head = rq->balance_callback;
 
 	lockdep_assert_held(&rq->lock);
-	if (head) {
+	if (head)
 		rq->balance_callback = NULL;
-		rq->balance_flags &= ~BALANCE_WORK;
-	}
 
 	return head;
 }
@@ -4014,21 +4019,6 @@ static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
 	}
 }
 
-static void balance_push(struct rq *rq);
-
-static inline void balance_switch(struct rq *rq)
-{
-	if (likely(!rq->balance_flags))
-		return;
-
-	if (rq->balance_flags & BALANCE_PUSH) {
-		balance_push(rq);
-		return;
-	}
-
-	__balance_callbacks(rq);
-}
-
 #else
 
 static inline void __balance_callbacks(struct rq *rq)
@@ -4044,10 +4034,6 @@ static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
 {
 }
 
-static inline void balance_switch(struct rq *rq)
-{
-}
-
 #endif
 
 static inline void
@@ -4075,7 +4061,7 @@ static inline void finish_lock_switch(struct rq *rq)
 	 * prev into current:
 	 */
 	spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
-	balance_switch(rq);
+	__balance_callbacks(rq);
 	raw_spin_unlock_irq(&rq->lock);
 }
 
@@ -7256,6 +7242,10 @@ static void balance_push(struct rq *rq)
 
 	lockdep_assert_held(&rq->lock);
 	SCHED_WARN_ON(rq->cpu != smp_processor_id());
+	/*
+	 * Ensure the thing is persistent until balance_push_set(.on = false);
+	 */
+	rq->balance_callback = &balance_push_callback;
 
 	/*
 	 * Both the cpu-hotplug and stop task are in this case and are
@@ -7305,9 +7295,9 @@ static void balance_push_set(int cpu, bool on)
 
 	rq_lock_irqsave(rq, &rf);
 	if (on)
-		rq->balance_flags |= BALANCE_PUSH;
+		rq->balance_callback = &balance_push_callback;
 	else
-		rq->balance_flags &= ~BALANCE_PUSH;
+		rq->balance_callback = NULL;
 	rq_unlock_irqrestore(rq, &rf);
 }
 

kernel/sched/sched.h

@@ -975,7 +975,6 @@ struct rq {
 	unsigned long		cpu_capacity_orig;
 
 	struct callback_head	*balance_callback;
-	unsigned char		balance_flags;
 
 	unsigned char		nohz_idle_balance;
 	unsigned char		idle_balance;
@@ -1226,6 +1225,8 @@ struct rq_flags {
 #endif
 };
 
+extern struct callback_head balance_push_callback;
+
 /*
  * Lockdep annotation that avoids accidental unlocks; it's like a
  * sticky/continuous lockdep_assert_held().
@@ -1243,9 +1244,9 @@ static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
 #ifdef CONFIG_SCHED_DEBUG
 	rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
 	rf->clock_update_flags = 0;
-#endif
 #ifdef CONFIG_SMP
-	SCHED_WARN_ON(rq->balance_callback);
+	SCHED_WARN_ON(rq->balance_callback && rq->balance_callback != &balance_push_callback);
+#endif
 #endif
 }
 
@@ -1408,9 +1409,6 @@ init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
 
 #ifdef CONFIG_SMP
 
-#define BALANCE_WORK	0x01
-#define BALANCE_PUSH	0x02
-
 static inline void
 queue_balance_callback(struct rq *rq,
 		       struct callback_head *head,
@@ -1418,13 +1416,12 @@ queue_balance_callback(struct rq *rq,
 {
 	lockdep_assert_held(&rq->lock);
 
-	if (unlikely(head->next || (rq->balance_flags & BALANCE_PUSH)))
+	if (unlikely(head->next || rq->balance_callback == &balance_push_callback))
 		return;
 
 	head->func = (void (*)(struct callback_head *))func;
 	head->next = rq->balance_callback;
 	rq->balance_callback = head;
-	rq->balance_flags |= BALANCE_WORK;
 }
 
 #define rcu_dereference_check_sched_domain(p) \