[PATCH 6/9] sched: Push put_prev_task() into pick_next_task()

From: Peter Zijlstra
Date: Tue Jan 21 2014 - 06:30:00 EST


In order to avoid having to do put/set on a whole cgroup hierarchy
when we context switch, push the put into pick_next_task() so that
both operations are in the same function. Further changes then allow
us to possibly optimize away redundant work.

Signed-off-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/1328936700.2476.17.camel@laptop
---
kernel/sched/core.c | 21 ++++++++-------------
kernel/sched/deadline.c | 2 +-
kernel/sched/fair.c | 6 +++++-
kernel/sched/idle_task.c | 6 +++++-
kernel/sched/rt.c | 27 ++++++++++++++++-----------
kernel/sched/sched.h | 8 +++++++-
kernel/sched/stop_task.c | 5 ++++-
7 files changed, 46 insertions(+), 29 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2554,18 +2554,11 @@ static inline void schedule_debug(struct
schedstat_inc(this_rq(), sched_count);
}

-static void put_prev_task(struct rq *rq, struct task_struct *prev)
-{
- if (prev->on_rq || rq->skip_clock_update < 0)
- update_rq_clock(rq);
- prev->sched_class->put_prev_task(rq, prev);
-}
-
/*
* Pick up the highest-prio task:
*/
static inline struct task_struct *
-pick_next_task(struct rq *rq)
+pick_next_task(struct rq *rq, struct task_struct *prev)
{
const struct sched_class *class;
struct task_struct *p;
@@ -2575,13 +2568,13 @@ pick_next_task(struct rq *rq)
* the fair class we can call that function directly:
*/
if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
- p = fair_sched_class.pick_next_task(rq);
+ p = fair_sched_class.pick_next_task(rq, prev);
if (likely(p))
return p;
}

for_each_class(class) {
- p = class->pick_next_task(rq);
+ p = class->pick_next_task(rq, prev);
if (p)
return p;
}
@@ -2682,8 +2675,10 @@ static void __sched __schedule(void)
if (unlikely(!rq->nr_running))
rq->idle_stamp = idle_balance(rq) ? 0 : rq_clock(rq);

- put_prev_task(rq, prev);
- next = pick_next_task(rq);
+ if (prev->on_rq || rq->skip_clock_update < 0)
+ update_rq_clock(rq);
+
+ next = pick_next_task(rq, prev);
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
rq->skip_clock_update = 0;
@@ -4725,7 +4720,7 @@ static void migrate_tasks(unsigned int d
if (rq->nr_running == 1)
break;

- next = pick_next_task(rq);
+ next = pick_next_task(rq, NULL);
BUG_ON(!next);
next->sched_class->put_prev_task(rq, next);

--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -989,7 +989,7 @@ static struct sched_dl_entity *pick_next
return rb_entry(left, struct sched_dl_entity, rb_node);
}

-struct task_struct *pick_next_task_dl(struct rq *rq)
+struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev)
{
struct sched_dl_entity *dl_se;
struct task_struct *p;
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4484,7 +4484,8 @@ static void check_preempt_wakeup(struct
set_last_buddy(se);
}

-static struct task_struct *pick_next_task_fair(struct rq *rq)
+static struct task_struct *
+pick_next_task_fair(struct rq *rq, struct task_struct *prev)
{
struct task_struct *p;
struct cfs_rq *cfs_rq = &rq->cfs;
@@ -4493,6 +4494,9 @@ static struct task_struct *pick_next_tas
if (!cfs_rq->nr_running)
return NULL;

+ if (prev)
+ prev->sched_class->put_prev_task(rq, prev);
+
do {
se = pick_next_entity(cfs_rq);
set_next_entity(cfs_rq, se);
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -23,8 +23,12 @@ static void check_preempt_curr_idle(stru
resched_task(rq->idle);
}

-static struct task_struct *pick_next_task_idle(struct rq *rq)
+static struct task_struct *
+pick_next_task_idle(struct rq *rq, struct task_struct *prev)
{
+ if (prev)
+ prev->sched_class->put_prev_task(rq, prev);
+
schedstat_inc(rq, sched_goidle);
#ifdef CONFIG_SMP
idle_enter_fair(rq);
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1310,15 +1310,7 @@ static struct task_struct *_pick_next_ta
{
struct sched_rt_entity *rt_se;
struct task_struct *p;
- struct rt_rq *rt_rq;
-
- rt_rq = &rq->rt;
-
- if (!rt_rq->rt_nr_running)
- return NULL;
-
- if (rt_rq_throttled(rt_rq))
- return NULL;
+ struct rt_rq *rt_rq = &rq->rt;

do {
rt_se = pick_next_rt_entity(rq, rt_rq);
@@ -1332,9 +1324,22 @@ static struct task_struct *_pick_next_ta
return p;
}

-static struct task_struct *pick_next_task_rt(struct rq *rq)
+static struct task_struct *
+pick_next_task_rt(struct rq *rq, struct task_struct *prev)
{
- struct task_struct *p = _pick_next_task_rt(rq);
+ struct task_struct *p;
+ struct rt_rq *rt_rq = &rq->rt;
+
+ if (!rt_rq->rt_nr_running)
+ return NULL;
+
+ if (rt_rq_throttled(rt_rq))
+ return NULL;
+
+ if (prev)
+ prev->sched_class->put_prev_task(rq, prev);
+
+ p = _pick_next_task_rt(rq);

/* The running task is never eligible for pushing */
if (p)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1123,7 +1123,13 @@ struct sched_class {

void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);

- struct task_struct * (*pick_next_task) (struct rq *rq);
+ /*
+ * It is the responsibility of the pick_next_task() method that will
+ * return the next task to call put_prev_task() on the @prev task or
+ * something equivalent.
+ */
+ struct task_struct * (*pick_next_task) (struct rq *rq,
+ struct task_struct *prev);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);

#ifdef CONFIG_SMP
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -23,11 +23,14 @@ check_preempt_curr_stop(struct rq *rq, s
/* we're never preempted */
}

-static struct task_struct *pick_next_task_stop(struct rq *rq)
+static struct task_struct *
+pick_next_task_stop(struct rq *rq, struct task_struct *prev)
{
struct task_struct *stop = rq->stop;

if (stop && stop->on_rq) {
+ if (prev)
+ prev->sched_class->put_prev_task(rq, prev);
stop->se.exec_start = rq_clock_task(rq);
return stop;
}


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/