sched: Provide p->on_rq
Provide a generic p->on_rq because the p->se.on_rq semantics are
unfavourable for lockless wakeups but needed for sched_fair.
In particular, p->on_rq is only cleared when we actually dequeue the
task in schedule() and not on any random dequeue as done by things
like __migrate_task() and __sched_setscheduler().
This also allows us to remove p->se usage from !sched_fair code.
Reviewed-by: Frank Rowand <frank.rowand@am.sony.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110405152728.949545047@chello.nl
diff --git a/kernel/sched.c b/kernel/sched.c
index 4481638..dece28e 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1785,7 +1785,6 @@
update_rq_clock(rq);
sched_info_queued(p);
p->sched_class->enqueue_task(rq, p, flags);
- p->se.on_rq = 1;
}
static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
@@ -1793,7 +1792,6 @@
update_rq_clock(rq);
sched_info_dequeued(p);
p->sched_class->dequeue_task(rq, p, flags);
- p->se.on_rq = 0;
}
/*
@@ -2128,7 +2126,7 @@
* A queue event has occurred, and we're going to schedule. In
* this case, we can save a useless back to back clock update.
*/
- if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr))
+ if (rq->curr->on_rq && test_tsk_need_resched(rq->curr))
rq->skip_clock_update = 1;
}
@@ -2203,7 +2201,7 @@
* If the task is not on a runqueue (and not running), then
* the next wake-up will properly place the task.
*/
- return p->se.on_rq || task_running(rq, p);
+ return p->on_rq || task_running(rq, p);
}
/*
@@ -2263,7 +2261,7 @@
rq = task_rq_lock(p, &flags);
trace_sched_wait_task(p);
running = task_running(rq, p);
- on_rq = p->se.on_rq;
+ on_rq = p->on_rq;
ncsw = 0;
if (!match_state || p->state == match_state)
ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
@@ -2444,6 +2442,7 @@
static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
{
activate_task(rq, p, en_flags);
+ p->on_rq = 1;
/* if a worker is waking up, notify workqueue */
if (p->flags & PF_WQ_WORKER)
@@ -2506,7 +2505,7 @@
cpu = task_cpu(p);
- if (p->se.on_rq)
+ if (p->on_rq)
goto out_running;
orig_cpu = cpu;
@@ -2583,7 +2582,7 @@
if (!(p->state & TASK_NORMAL))
return;
- if (!p->se.on_rq)
+ if (!p->on_rq)
ttwu_activate(rq, p, ENQUEUE_WAKEUP);
ttwu_post_activation(p, rq, 0);
@@ -2620,19 +2619,21 @@
*/
static void __sched_fork(struct task_struct *p)
{
+ p->on_rq = 0;
+
+ p->se.on_rq = 0;
p->se.exec_start = 0;
p->se.sum_exec_runtime = 0;
p->se.prev_sum_exec_runtime = 0;
p->se.nr_migrations = 0;
p->se.vruntime = 0;
+ INIT_LIST_HEAD(&p->se.group_node);
#ifdef CONFIG_SCHEDSTATS
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
#endif
INIT_LIST_HEAD(&p->rt.run_list);
- p->se.on_rq = 0;
- INIT_LIST_HEAD(&p->se.group_node);
#ifdef CONFIG_PREEMPT_NOTIFIERS
INIT_HLIST_HEAD(&p->preempt_notifiers);
@@ -2750,6 +2751,7 @@
rq = task_rq_lock(p, &flags);
activate_task(rq, p, 0);
+ p->on_rq = 1;
trace_sched_wakeup_new(p, true);
check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
@@ -4051,7 +4053,7 @@
static void put_prev_task(struct rq *rq, struct task_struct *prev)
{
- if (prev->se.on_rq)
+ if (prev->on_rq)
update_rq_clock(rq);
prev->sched_class->put_prev_task(rq, prev);
}
@@ -4126,7 +4128,9 @@
if (to_wakeup)
try_to_wake_up_local(to_wakeup);
}
+
deactivate_task(rq, prev, DEQUEUE_SLEEP);
+ prev->on_rq = 0;
/*
* If we are going to sleep and we have plugged IO queued, make
@@ -4695,7 +4699,7 @@
trace_sched_pi_setprio(p, prio);
oldprio = p->prio;
prev_class = p->sched_class;
- on_rq = p->se.on_rq;
+ on_rq = p->on_rq;
running = task_current(rq, p);
if (on_rq)
dequeue_task(rq, p, 0);
@@ -4743,7 +4747,7 @@
p->static_prio = NICE_TO_PRIO(nice);
goto out_unlock;
}
- on_rq = p->se.on_rq;
+ on_rq = p->on_rq;
if (on_rq)
dequeue_task(rq, p, 0);
@@ -4877,8 +4881,6 @@
static void
__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
{
- BUG_ON(p->se.on_rq);
-
p->policy = policy;
p->rt_priority = prio;
p->normal_prio = normal_prio(p);
@@ -5044,7 +5046,7 @@
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
goto recheck;
}
- on_rq = p->se.on_rq;
+ on_rq = p->on_rq;
running = task_current(rq, p);
if (on_rq)
deactivate_task(rq, p, 0);
@@ -5965,7 +5967,7 @@
* If we're not on a rq, the next wake-up will ensure we're
* placed properly.
*/
- if (p->se.on_rq) {
+ if (p->on_rq) {
deactivate_task(rq_src, p, 0);
set_task_cpu(p, dest_cpu);
activate_task(rq_dest, p, 0);
@@ -8339,7 +8341,7 @@
int old_prio = p->prio;
int on_rq;
- on_rq = p->se.on_rq;
+ on_rq = p->on_rq;
if (on_rq)
deactivate_task(rq, p, 0);
__setscheduler(rq, p, SCHED_NORMAL, 0);
@@ -8682,7 +8684,7 @@
rq = task_rq_lock(tsk, &flags);
running = task_current(rq, tsk);
- on_rq = tsk->se.on_rq;
+ on_rq = tsk->on_rq;
if (on_rq)
dequeue_task(rq, tsk, 0);