sched/debug: Remove several CONFIG_SCHEDSTATS guards

Clean up the sched code by removing several of the CONFIG_SCHEDSTATS
guards, using schedstat_*() macros where needed.

Code size:

  !CONFIG_SCHEDSTATS defconfig:

      text	   data	    bss	     dec	    hex	filename
  10209818	4368184	1105920	15683922	 ef5152	vmlinux.before.nostats
  10209818	4368184	1105920	15683922	 ef5152	vmlinux.after.nostats

  CONFIG_SCHEDSTATS defconfig:

      text	   data	    bss	    dec	    hex	filename
  10214210	4370040	1105920	15690170	 ef69ba	vmlinux.before.stats
  10214210	4370680	1105920	15690810	 ef6c3a	vmlinux.after.stats

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/e51e0ebe5af95ac295de720dd252e7c0d2142e4a.1466184592.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 136 insertions, 144 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8506770..860070f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1629,13 +1629,15 @@ static inline int __set_cpus_allowed_ptr(struct task_struct *p,
 static void
 ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 {
-#ifdef CONFIG_SCHEDSTATS
-	struct rq *rq = this_rq();
+	struct rq *rq;
 
-#ifdef CONFIG_SMP
-	int this_cpu = smp_processor_id();
+	if (!schedstat_enabled())
+		return;
+
+	rq = this_rq();
 
-	if (cpu == this_cpu) {
+#ifdef CONFIG_SMP
+	if (cpu == rq->cpu) {
 		schedstat_inc(rq->ttwu_local);
 		schedstat_inc(p->se.statistics.nr_wakeups_local);
 	} else {
@@ -1643,7 +1645,7 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 
 		schedstat_inc(p->se.statistics.nr_wakeups_remote);
 		rcu_read_lock();
-		for_each_domain(this_cpu, sd) {
+		for_each_domain(rq->cpu, sd) {
 			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
 				schedstat_inc(sd->ttwu_wake_remote);
 				break;
@@ -1654,7 +1656,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 
 	if (wake_flags & WF_MIGRATED)
 		schedstat_inc(p->se.statistics.nr_wakeups_migrate);
-
 #endif /* CONFIG_SMP */
 
 	schedstat_inc(rq->ttwu_count);
@@ -1662,8 +1663,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 
 	if (wake_flags & WF_SYNC)
 		schedstat_inc(p->se.statistics.nr_wakeups_sync);
-
-#endif /* CONFIG_SCHEDSTATS */
 }
 
 static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
@@ -2084,8 +2083,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 	ttwu_queue(p, cpu, wake_flags);
 stat:
-	if (schedstat_enabled())
-		ttwu_stat(p, cpu, wake_flags);
+	ttwu_stat(p, cpu, wake_flags);
 out:
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
@@ -2134,8 +2132,7 @@ static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
 
 	ttwu_do_wakeup(rq, p, 0, cookie);
-	if (schedstat_enabled())
-		ttwu_stat(p, smp_processor_id(), 0);
+	ttwu_stat(p, smp_processor_id(), 0);
 out:
 	raw_spin_unlock(&p->pi_lock);
 }
@@ -7675,12 +7672,10 @@ void normalize_rt_tasks(void)
 		if (p->flags & PF_KTHREAD)
 			continue;
 
-		p->se.exec_start		= 0;
-#ifdef CONFIG_SCHEDSTATS
-		p->se.statistics.wait_start	= 0;
-		p->se.statistics.sleep_start	= 0;
-		p->se.statistics.block_start	= 0;
-#endif
+		p->se.exec_start = 0;
+		schedstat_set(p->se.statistics.wait_start,  0);
+		schedstat_set(p->se.statistics.sleep_start, 0);
+		schedstat_set(p->se.statistics.block_start, 0);
 
 		if (!dl_task(p) && !rt_task(p)) {
 			/*
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 63ffcaa..1393588 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -369,8 +369,12 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 
 #define P(F) \
 	SEQ_printf(m, "  .%-30s: %lld\n", #F, (long long)F)
+#define P_SCHEDSTAT(F) \
+	SEQ_printf(m, "  .%-30s: %lld\n", #F, (long long)schedstat_val(F))
 #define PN(F) \
 	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))
+#define PN_SCHEDSTAT(F) \
+	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)schedstat_val(F)))
 
 	if (!se)
 		return;
@@ -378,26 +382,27 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	PN(se->exec_start);
 	PN(se->vruntime);
 	PN(se->sum_exec_runtime);
-#ifdef CONFIG_SCHEDSTATS
 	if (schedstat_enabled()) {
-		PN(se->statistics.wait_start);
-		PN(se->statistics.sleep_start);
-		PN(se->statistics.block_start);
-		PN(se->statistics.sleep_max);
-		PN(se->statistics.block_max);
-		PN(se->statistics.exec_max);
-		PN(se->statistics.slice_max);
-		PN(se->statistics.wait_max);
-		PN(se->statistics.wait_sum);
-		P(se->statistics.wait_count);
+		PN_SCHEDSTAT(se->statistics.wait_start);
+		PN_SCHEDSTAT(se->statistics.sleep_start);
+		PN_SCHEDSTAT(se->statistics.block_start);
+		PN_SCHEDSTAT(se->statistics.sleep_max);
+		PN_SCHEDSTAT(se->statistics.block_max);
+		PN_SCHEDSTAT(se->statistics.exec_max);
+		PN_SCHEDSTAT(se->statistics.slice_max);
+		PN_SCHEDSTAT(se->statistics.wait_max);
+		PN_SCHEDSTAT(se->statistics.wait_sum);
+		P_SCHEDSTAT(se->statistics.wait_count);
 	}
-#endif
 	P(se->load.weight);
 #ifdef CONFIG_SMP
 	P(se->avg.load_avg);
 	P(se->avg.util_avg);
 #endif
+
+#undef PN_SCHEDSTAT
 #undef PN
+#undef P_SCHEDSTAT
 #undef P
 }
 #endif
@@ -626,9 +631,7 @@ do {									\
 #undef P64
 #endif
 
-#ifdef CONFIG_SCHEDSTATS
-#define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
-
+#define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, schedstat_val(rq->n));
 	if (schedstat_enabled()) {
 		P(yld_count);
 		P(sched_count);
@@ -636,9 +639,8 @@ do {									\
 		P(ttwu_count);
 		P(ttwu_local);
 	}
-
 #undef P
-#endif
+
 	spin_lock_irqsave(&sched_debug_lock, flags);
 	print_cfs_stats(m, cpu);
 	print_rt_stats(m, cpu);
@@ -868,10 +870,14 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
 #define P(F) \
 	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
+#define P_SCHEDSTAT(F) \
+	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)schedstat_val(p->F))
 #define __PN(F) \
 	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
 #define PN(F) \
 	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
+#define PN_SCHEDSTAT(F) \
+	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)schedstat_val(p->F)))
 
 	PN(se.exec_start);
 	PN(se.vruntime);
@@ -881,37 +887,36 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 
 	P(se.nr_migrations);
 
-#ifdef CONFIG_SCHEDSTATS
 	if (schedstat_enabled()) {
 		u64 avg_atom, avg_per_cpu;
 
-		PN(se.statistics.sum_sleep_runtime);
-		PN(se.statistics.wait_start);
-		PN(se.statistics.sleep_start);
-		PN(se.statistics.block_start);
-		PN(se.statistics.sleep_max);
-		PN(se.statistics.block_max);
-		PN(se.statistics.exec_max);
-		PN(se.statistics.slice_max);
-		PN(se.statistics.wait_max);
-		PN(se.statistics.wait_sum);
-		P(se.statistics.wait_count);
-		PN(se.statistics.iowait_sum);
-		P(se.statistics.iowait_count);
-		P(se.statistics.nr_migrations_cold);
-		P(se.statistics.nr_failed_migrations_affine);
-		P(se.statistics.nr_failed_migrations_running);
-		P(se.statistics.nr_failed_migrations_hot);
-		P(se.statistics.nr_forced_migrations);
-		P(se.statistics.nr_wakeups);
-		P(se.statistics.nr_wakeups_sync);
-		P(se.statistics.nr_wakeups_migrate);
-		P(se.statistics.nr_wakeups_local);
-		P(se.statistics.nr_wakeups_remote);
-		P(se.statistics.nr_wakeups_affine);
-		P(se.statistics.nr_wakeups_affine_attempts);
-		P(se.statistics.nr_wakeups_passive);
-		P(se.statistics.nr_wakeups_idle);
+		PN_SCHEDSTAT(se.statistics.sum_sleep_runtime);
+		PN_SCHEDSTAT(se.statistics.wait_start);
+		PN_SCHEDSTAT(se.statistics.sleep_start);
+		PN_SCHEDSTAT(se.statistics.block_start);
+		PN_SCHEDSTAT(se.statistics.sleep_max);
+		PN_SCHEDSTAT(se.statistics.block_max);
+		PN_SCHEDSTAT(se.statistics.exec_max);
+		PN_SCHEDSTAT(se.statistics.slice_max);
+		PN_SCHEDSTAT(se.statistics.wait_max);
+		PN_SCHEDSTAT(se.statistics.wait_sum);
+		P_SCHEDSTAT(se.statistics.wait_count);
+		PN_SCHEDSTAT(se.statistics.iowait_sum);
+		P_SCHEDSTAT(se.statistics.iowait_count);
+		P_SCHEDSTAT(se.statistics.nr_migrations_cold);
+		P_SCHEDSTAT(se.statistics.nr_failed_migrations_affine);
+		P_SCHEDSTAT(se.statistics.nr_failed_migrations_running);
+		P_SCHEDSTAT(se.statistics.nr_failed_migrations_hot);
+		P_SCHEDSTAT(se.statistics.nr_forced_migrations);
+		P_SCHEDSTAT(se.statistics.nr_wakeups);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_sync);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_migrate);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_local);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_remote);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_affine);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_affine_attempts);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_passive);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_idle);
 
 		avg_atom = p->se.sum_exec_runtime;
 		if (nr_switches)
@@ -930,7 +935,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 		__PN(avg_atom);
 		__PN(avg_per_cpu);
 	}
-#endif
+
 	__P(nr_switches);
 	SEQ_printf(m, "%-45s:%21Ld\n",
 		   "nr_voluntary_switches", (long long)p->nvcsw);
@@ -947,8 +952,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 #endif
 	P(policy);
 	P(prio);
+#undef PN_SCHEDSTAT
 #undef PN
 #undef __PN
+#undef P_SCHEDSTAT
 #undef P
 #undef __P
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 157d741..a6820b3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -821,26 +821,34 @@ static void update_curr_fair(struct rq *rq)
 	update_curr(cfs_rq_of(&rq->curr->se));
 }
 
-#ifdef CONFIG_SCHEDSTATS
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u64 wait_start = rq_clock(rq_of(cfs_rq));
+	u64 wait_start, prev_wait_start;
+
+	if (!schedstat_enabled())
+		return;
+
+	wait_start = rq_clock(rq_of(cfs_rq));
+	prev_wait_start = schedstat_val(se->statistics.wait_start);
 
 	if (entity_is_task(se) && task_on_rq_migrating(task_of(se)) &&
-	    likely(wait_start > se->statistics.wait_start))
-		wait_start -= se->statistics.wait_start;
+	    likely(wait_start > prev_wait_start))
+		wait_start -= prev_wait_start;
 
-	se->statistics.wait_start = wait_start;
+	schedstat_set(se->statistics.wait_start, wait_start);
 }
 
-static void
+static inline void
 update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	struct task_struct *p;
 	u64 delta;
 
-	delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start;
+	if (!schedstat_enabled())
+		return;
+
+	delta = rq_clock(rq_of(cfs_rq)) - schedstat_val(se->statistics.wait_start);
 
 	if (entity_is_task(se)) {
 		p = task_of(se);
@@ -850,59 +858,67 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 			 * time stamp can be adjusted to accumulate wait time
 			 * prior to migration.
 			 */
-			se->statistics.wait_start = delta;
+			schedstat_set(se->statistics.wait_start, delta);
 			return;
 		}
 		trace_sched_stat_wait(p, delta);
 	}
 
-	se->statistics.wait_max = max(se->statistics.wait_max, delta);
-	se->statistics.wait_count++;
-	se->statistics.wait_sum += delta;
-	se->statistics.wait_start = 0;
+	schedstat_set(se->statistics.wait_max,
+		      max(schedstat_val(se->statistics.wait_max), delta));
+	schedstat_inc(se->statistics.wait_count);
+	schedstat_add(se->statistics.wait_sum, delta);
+	schedstat_set(se->statistics.wait_start, 0);
 }
 
-static void
+static inline void
 update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	struct task_struct *tsk = NULL;
+	u64 sleep_start, block_start;
+
+	if (!schedstat_enabled())
+		return;
+
+	sleep_start = schedstat_val(se->statistics.sleep_start);
+	block_start = schedstat_val(se->statistics.block_start);
 
 	if (entity_is_task(se))
 		tsk = task_of(se);
 
-	if (se->statistics.sleep_start) {
-		u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.sleep_start;
+	if (sleep_start) {
+		u64 delta = rq_clock(rq_of(cfs_rq)) - sleep_start;
 
 		if ((s64)delta < 0)
 			delta = 0;
 
-		if (unlikely(delta > se->statistics.sleep_max))
-			se->statistics.sleep_max = delta;
+		if (unlikely(delta > schedstat_val(se->statistics.sleep_max)))
+			schedstat_set(se->statistics.sleep_max, delta);
 
-		se->statistics.sleep_start = 0;
-		se->statistics.sum_sleep_runtime += delta;
+		schedstat_set(se->statistics.sleep_start, 0);
+		schedstat_add(se->statistics.sum_sleep_runtime, delta);
 
 		if (tsk) {
 			account_scheduler_latency(tsk, delta >> 10, 1);
 			trace_sched_stat_sleep(tsk, delta);
 		}
 	}
-	if (se->statistics.block_start) {
-		u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.block_start;
+	if (block_start) {
+		u64 delta = rq_clock(rq_of(cfs_rq)) - block_start;
 
 		if ((s64)delta < 0)
 			delta = 0;
 
-		if (unlikely(delta > se->statistics.block_max))
-			se->statistics.block_max = delta;
+		if (unlikely(delta > schedstat_val(se->statistics.block_max)))
+			schedstat_set(se->statistics.block_max, delta);
 
-		se->statistics.block_start = 0;
-		se->statistics.sum_sleep_runtime += delta;
+		schedstat_set(se->statistics.block_start, 0);
+		schedstat_add(se->statistics.sum_sleep_runtime, delta);
 
 		if (tsk) {
 			if (tsk->in_iowait) {
-				se->statistics.iowait_sum += delta;
-				se->statistics.iowait_count++;
+				schedstat_add(se->statistics.iowait_sum, delta);
+				schedstat_inc(se->statistics.iowait_count);
 				trace_sched_stat_iowait(tsk, delta);
 			}
 
@@ -929,6 +945,9 @@ update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static inline void
 update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
+	if (!schedstat_enabled())
+		return;
+
 	/*
 	 * Are we enqueueing a waiting task? (for current tasks
 	 * a dequeue/enqueue event is a NOP)
@@ -943,6 +962,10 @@ update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 static inline void
 update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
+
+	if (!schedstat_enabled())
+		return;
+
 	/*
 	 * Mark the end of the wait period if dequeueing a
 	 * waiting task:
@@ -950,45 +973,18 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	if (se != cfs_rq->curr)
 		update_stats_wait_end(cfs_rq, se);
 
-	if (flags & DEQUEUE_SLEEP) {
-		if (entity_is_task(se)) {
-			struct task_struct *tsk = task_of(se);
+	if ((flags & DEQUEUE_SLEEP) && entity_is_task(se)) {
+		struct task_struct *tsk = task_of(se);
 
-			if (tsk->state & TASK_INTERRUPTIBLE)
-				se->statistics.sleep_start = rq_clock(rq_of(cfs_rq));
-			if (tsk->state & TASK_UNINTERRUPTIBLE)
-				se->statistics.block_start = rq_clock(rq_of(cfs_rq));
-		}
+		if (tsk->state & TASK_INTERRUPTIBLE)
+			schedstat_set(se->statistics.sleep_start,
+				      rq_clock(rq_of(cfs_rq)));
+		if (tsk->state & TASK_UNINTERRUPTIBLE)
+			schedstat_set(se->statistics.block_start,
+				      rq_clock(rq_of(cfs_rq)));
 	}
-
-}
-#else
-static inline void
-update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-}
-
-static inline void
-update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-}
-
-static inline void
-update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
 }
 
-static inline void
-update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
-{
-}
-
-static inline void
-update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
-{
-}
-#endif
-
 /*
  * We are picking a new current task - update its stats:
  */
@@ -3396,10 +3392,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		place_entity(cfs_rq, se, 0);
 
 	check_schedstat_required();
-	if (schedstat_enabled()) {
-		update_stats_enqueue(cfs_rq, se, flags);
-		check_spread(cfs_rq, se);
-	}
+	update_stats_enqueue(cfs_rq, se, flags);
+	check_spread(cfs_rq, se);
 	if (!curr)
 		__enqueue_entity(cfs_rq, se);
 	se->on_rq = 1;
@@ -3466,8 +3460,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	update_curr(cfs_rq);
 	dequeue_entity_load_avg(cfs_rq, se);
 
-	if (schedstat_enabled())
-		update_stats_dequeue(cfs_rq, se, flags);
+	update_stats_dequeue(cfs_rq, se, flags);
 
 	clear_buddies(cfs_rq, se);
 
@@ -3541,25 +3534,25 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		 * a CPU. So account for the time it spent waiting on the
 		 * runqueue.
 		 */
-		if (schedstat_enabled())
-			update_stats_wait_end(cfs_rq, se);
+		update_stats_wait_end(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
 		update_load_avg(se, 1);
 	}
 
 	update_stats_curr_start(cfs_rq, se);
 	cfs_rq->curr = se;
-#ifdef CONFIG_SCHEDSTATS
+
 	/*
 	 * Track our maximum slice length, if the CPU's load is at
 	 * least twice that of our own weight (i.e. dont track it
 	 * when there are only lesser-weight tasks around):
 	 */
 	if (schedstat_enabled() && rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
-		se->statistics.slice_max = max(se->statistics.slice_max,
-			se->sum_exec_runtime - se->prev_sum_exec_runtime);
+		schedstat_set(se->statistics.slice_max,
+			max((u64)schedstat_val(se->statistics.slice_max),
+			    se->sum_exec_runtime - se->prev_sum_exec_runtime));
 	}
-#endif
+
 	se->prev_sum_exec_runtime = se->sum_exec_runtime;
 }
 
@@ -3638,13 +3631,10 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 	/* throttle cfs_rqs exceeding runtime */
 	check_cfs_rq_runtime(cfs_rq);
 
-	if (schedstat_enabled()) {
-		check_spread(cfs_rq, prev);
-		if (prev->on_rq)
-			update_stats_wait_start(cfs_rq, prev);
-	}
+	check_spread(cfs_rq, prev);
 
 	if (prev->on_rq) {
+		update_stats_wait_start(cfs_rq, prev);
 		/* Put 'current' back into the tree. */
 		__enqueue_entity(cfs_rq, prev);
 		/* in !on_rq case, update occurred at dequeue */