sched: uninline scheduler

* save ~300 bytes
* activate_idle_task() was moved to avoid a warning

bloat-o-meter output:

add/remove: 6/0 grow/shrink: 0/16 up/down: 438/-733 (-295)		<===
function                                     old     new   delta
__enqueue_entity                               -     165    +165
finish_task_switch                             -     110    +110
update_curr_rt                                 -      79     +79
__load_balance_iterator                        -      32     +32
__task_rq_unlock                               -      28     +28
find_process_by_pid                            -      24     +24
do_sched_setscheduler                        133     123     -10
sys_sched_rr_get_interval                    176     165     -11
sys_sched_getparam                           156     145     -11
normalize_rt_tasks                           482     470     -12
sched_getaffinity                            112      99     -13
sys_sched_getscheduler                        86      72     -14
sched_setaffinity                            226     212     -14
sched_setscheduler                           666     642     -24
load_balance_start_fair                       33       9     -24
load_balance_next_fair                        33       9     -24
dequeue_task_rt                              133      67     -66
put_prev_task_rt                              97      28     -69
schedule_tail                                133      50     -83
schedule                                     682     594     -88
enqueue_entity                               499     366    -133
task_new_fair                                317     180    -137
Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/sched.c

@@ -608,7 +608,7 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
 	return rq;
 }
 
-static inline void __task_rq_unlock(struct rq *rq)
+static void __task_rq_unlock(struct rq *rq)
 	__releases(rq->lock)
 {
 	spin_unlock(&rq->lock);
@@ -623,7 +623,7 @@ static inline void task_rq_unlock(struct rq *rq, unsigned long *flags)
 /*
  * this_rq_lock - lock this runqueue and disable interrupts.
  */
-static inline struct rq *this_rq_lock(void)
+static struct rq *this_rq_lock(void)
 	__acquires(rq->lock)
 {
 	struct rq *rq;
@@ -985,20 +985,6 @@ static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
 	inc_nr_running(p, rq);
 }
 
-/*
- * activate_idle_task - move idle task to the _front_ of runqueue.
- */
-static inline void activate_idle_task(struct task_struct *p, struct rq *rq)
-{
-	update_rq_clock(rq);
-
-	if (p->state == TASK_UNINTERRUPTIBLE)
-		rq->nr_uninterruptible--;
-
-	enqueue_task(rq, p, 0);
-	inc_nr_running(p, rq);
-}
-
 /*
  * deactivate_task - remove a task from the runqueue.
  */
@@ -1206,7 +1192,7 @@ void kick_process(struct task_struct *p)
  * We want to under-estimate the load of migration sources, to
  * balance conservatively.
  */
-static inline unsigned long source_load(int cpu, int type)
+static unsigned long source_load(int cpu, int type)
 {
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long total = weighted_cpuload(cpu);
@@ -1221,7 +1207,7 @@ static inline unsigned long source_load(int cpu, int type)
  * Return a high guess at the load of a migration-target cpu weighted
  * according to the scheduling class and "nice" value.
  */
-static inline unsigned long target_load(int cpu, int type)
+static unsigned long target_load(int cpu, int type)
 {
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long total = weighted_cpuload(cpu);
@@ -1813,7 +1799,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
  * with the lock held can cause deadlocks; see schedule() for
  * details.)
  */
-static inline void finish_task_switch(struct rq *rq, struct task_struct *prev)
+static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	__releases(rq->lock)
 {
 	struct mm_struct *mm = rq->prev_mm;
@@ -3020,7 +3006,7 @@ static DEFINE_SPINLOCK(balancing);
  *
  * Balancing parameters are set up in arch_init_sched_domains.
  */
-static inline void rebalance_domains(int cpu, enum cpu_idle_type idle)
+static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 {
 	int balance = 1;
 	struct rq *rq = cpu_rq(cpu);
@@ -4140,7 +4126,7 @@ struct task_struct *idle_task(int cpu)
  * find_process_by_pid - find a process with a matching PID value.
  * @pid: the pid in question.
  */
-static inline struct task_struct *find_process_by_pid(pid_t pid)
+static struct task_struct *find_process_by_pid(pid_t pid)
 {
 	return pid ? find_task_by_pid(pid) : current;
 }
@@ -5156,6 +5142,20 @@ static void migrate_live_tasks(int src_cpu)
 	write_unlock_irq(&tasklist_lock);
 }
 
+/*
+ * activate_idle_task - move idle task to the _front_ of runqueue.
+ */
+static void activate_idle_task(struct task_struct *p, struct rq *rq)
+{
+	update_rq_clock(rq);
+
+	if (p->state == TASK_UNINTERRUPTIBLE)
+		rq->nr_uninterruptible--;
+
+	enqueue_task(rq, p, 0);
+	inc_nr_running(p, rq);
+}
+
 /*
  * Schedules idle task to be the next runnable task on current CPU.
  * It does so by boosting its priority to highest possible and adding it to
@@ -6494,7 +6494,7 @@ int in_sched_functions(unsigned long addr)
 		&& addr < (unsigned long)__sched_text_end);
 }
 
-static inline void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
+static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
 {
 	cfs_rq->tasks_timeline = RB_ROOT;
 #ifdef CONFIG_FAIR_GROUP_SCHED

kernel/sched_fair.c

@@ -892,7 +892,7 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
  * achieve that by always pre-iterating before returning
  * the current task:
  */
-static inline struct task_struct *
+static struct task_struct *
 __load_balance_iterator(struct cfs_rq *cfs_rq, struct rb_node *curr)
 {
 	struct task_struct *p;

kernel/sched_rt.c

@@ -7,7 +7,7 @@
  * Update the current task's runtime statistics. Skip current tasks that
  * are not in our scheduling class.
  */
-static inline void update_curr_rt(struct rq *rq)
+static void update_curr_rt(struct rq *rq)
 {
 	struct task_struct *curr = rq->curr;
 	u64 delta_exec;