sched/core: Move task_rq_lock() out of line

Its a rather large function, inline doesn't seems to make much sense:

 $ size defconfig-build/kernel/sched/core.o{.orig,}
    text    data     bss     dec     hex filename
   56533   21037    2320   79890   13812 defconfig-build/kernel/sched/core.o.orig
   55733   21037    2320   79090   134f2 defconfig-build/kernel/sched/core.o

The 'perf bench sched messaging' micro-benchmark shows a visible improvement
of 4-5%:

  $ for i in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor ; do echo performance > $i ; done
  $ perf stat --null --repeat 25 -- perf bench sched messaging -g 40 -l 5000

  pre:
       4.582798193 seconds time elapsed          ( +-  1.41% )
       4.733374877 seconds time elapsed          ( +-  2.10% )
       4.560955136 seconds time elapsed          ( +-  1.43% )
       4.631062303 seconds time elapsed          ( +-  1.40% )

  post:
       4.364765213 seconds time elapsed          ( +-  0.91% )
       4.454442734 seconds time elapsed          ( +-  1.18% )
       4.448893817 seconds time elapsed          ( +-  1.41% )
       4.424346872 seconds time elapsed          ( +-  0.97% )
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/core.c

@@ -170,6 +170,71 @@ static struct rq *this_rq_lock(void)
 	return rq;
 }
 
+/*
+ * __task_rq_lock - lock the rq @p resides on.
+ */
+struct rq *__task_rq_lock(struct task_struct *p)
+	__acquires(rq->lock)
+{
+	struct rq *rq;
+
+	lockdep_assert_held(&p->pi_lock);
+
+	for (;;) {
+		rq = task_rq(p);
+		raw_spin_lock(&rq->lock);
+		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
+			lockdep_pin_lock(&rq->lock);
+			return rq;
+		}
+		raw_spin_unlock(&rq->lock);
+
+		while (unlikely(task_on_rq_migrating(p)))
+			cpu_relax();
+	}
+}
+
+/*
+ * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
+ */
+struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
+	__acquires(p->pi_lock)
+	__acquires(rq->lock)
+{
+	struct rq *rq;
+
+	for (;;) {
+		raw_spin_lock_irqsave(&p->pi_lock, *flags);
+		rq = task_rq(p);
+		raw_spin_lock(&rq->lock);
+		/*
+		 *	move_queued_task()		task_rq_lock()
+		 *
+		 *	ACQUIRE (rq->lock)
+		 *	[S] ->on_rq = MIGRATING		[L] rq = task_rq()
+		 *	WMB (__set_task_cpu())		ACQUIRE (rq->lock);
+		 *	[S] ->cpu = new_cpu		[L] task_rq()
+		 *					[L] ->on_rq
+		 *	RELEASE (rq->lock)
+		 *
+		 * If we observe the old cpu in task_rq_lock, the acquire of
+		 * the old rq->lock will fully serialize against the stores.
+		 *
+		 * If we observe the new cpu in task_rq_lock, the acquire will
+		 * pair with the WMB to ensure we must then also see migrating.
+		 */
+		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
+			lockdep_pin_lock(&rq->lock);
+			return rq;
+		}
+		raw_spin_unlock(&rq->lock);
+		raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
+
+		while (unlikely(task_on_rq_migrating(p)))
+			cpu_relax();
+	}
+}
+
 #ifdef CONFIG_SCHED_HRTICK
 /*
  * Use HR-timers to deliver accurate preemption points.

kernel/sched/sched.h

@@ -1451,70 +1451,11 @@ static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
 static inline void sched_avg_update(struct rq *rq) { }
 #endif
 
-/*
- * __task_rq_lock - lock the rq @p resides on.
- */
-static inline struct rq *__task_rq_lock(struct task_struct *p)
-	__acquires(rq->lock)
-{
-	struct rq *rq;
-
-	lockdep_assert_held(&p->pi_lock);
-
-	for (;;) {
-		rq = task_rq(p);
-		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
-			lockdep_pin_lock(&rq->lock);
-			return rq;
-		}
-		raw_spin_unlock(&rq->lock);
-
-		while (unlikely(task_on_rq_migrating(p)))
-			cpu_relax();
-	}
-}
-
-/*
- * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
- */
-static inline struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
+struct rq *__task_rq_lock(struct task_struct *p)
+	__acquires(rq->lock);
+struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
 	__acquires(p->pi_lock)
-	__acquires(rq->lock)
-{
-	struct rq *rq;
-
-	for (;;) {
-		raw_spin_lock_irqsave(&p->pi_lock, *flags);
-		rq = task_rq(p);
-		raw_spin_lock(&rq->lock);
-		/*
-		 *	move_queued_task()		task_rq_lock()
-		 *
-		 *	ACQUIRE (rq->lock)
-		 *	[S] ->on_rq = MIGRATING		[L] rq = task_rq()
-		 *	WMB (__set_task_cpu())		ACQUIRE (rq->lock);
-		 *	[S] ->cpu = new_cpu		[L] task_rq()
-		 *					[L] ->on_rq
-		 *	RELEASE (rq->lock)
-		 *
-		 * If we observe the old cpu in task_rq_lock, the acquire of
-		 * the old rq->lock will fully serialize against the stores.
-		 *
-		 * If we observe the new cpu in task_rq_lock, the acquire will
-		 * pair with the WMB to ensure we must then also see migrating.
-		 */
-		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
-			lockdep_pin_lock(&rq->lock);
-			return rq;
-		}
-		raw_spin_unlock(&rq->lock);
-		raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
-
-		while (unlikely(task_on_rq_migrating(p)))
-			cpu_relax();
-	}
-}
+	__acquires(rq->lock);
 
 static inline void __task_rq_unlock(struct rq *rq)
 	__releases(rq->lock)