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

5 files changed, 31 insertions, 28 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 173850479e2c..b33a700652dc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1202,6 +1202,7 @@ struct task_struct {
 #ifdef CONFIG_SMP
         int on_cpu;
 #endif
+        int on_rq;
 
         int prio, static_prio, normal_prio;
         unsigned int rt_priority;
diff --git a/kernel/sched.c b/kernel/sched.c
index 4481638f9178..dece28e505c9 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1785,7 +1785,6 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
         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 @@ static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
         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 @@ static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
          * 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 @@ static bool migrate_task(struct task_struct *p, struct rq *rq)
          * 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 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
                 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 @@ ttwu_stat(struct rq *rq, struct task_struct *p, int cpu, int wake_flags)
 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 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 
         cpu = task_cpu(p);
 
-        if (p->se.on_rq)
+        if (p->on_rq)
                 goto out_running;
 
         orig_cpu = cpu;
@@ -2583,7 +2582,7 @@ static void try_to_wake_up_local(struct task_struct *p)
         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 @@ int wake_up_state(struct task_struct *p, unsigned int state)
  */
 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 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 
         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 inline void schedule_debug(struct task_struct *prev)
 
 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 @@ need_resched:
                                 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 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
         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 @@ void set_user_nice(struct task_struct *p, long nice)
                 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 struct task_struct *find_process_by_pid(pid_t pid)
 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 @@ recheck:
                 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 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
          * 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 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
         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 @@ void sched_move_task(struct task_struct *tsk)
         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);
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 7bacd83a4158..3669bec6e130 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -152,7 +152,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
         read_lock_irqsave(&tasklist_lock, flags);
 
         do_each_thread(g, p) {
-                if (!p->se.on_rq || task_cpu(p) != rq_cpu)
+                if (!p->on_rq || task_cpu(p) != rq_cpu)
                         continue;
 
                 print_task(m, rq, p);
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index e7cebdc65f82..9ca4f5f879c4 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1136,7 +1136,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
          * The previous task needs to be made eligible for pushing
          * if it is still active
          */
-        if (p->se.on_rq && p->rt.nr_cpus_allowed > 1)
+        if (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1)
                 enqueue_pushable_task(rq, p);
 }
 
@@ -1287,7 +1287,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
                                      !cpumask_test_cpu(lowest_rq->cpu,
                                                        &task->cpus_allowed) ||
                                      task_running(rq, task) ||
-                                     !task->se.on_rq)) {
+                                     !task->on_rq)) {
 
                                 raw_spin_unlock(&lowest_rq->lock);
                                 lowest_rq = NULL;
@@ -1321,7 +1321,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)
         BUG_ON(task_current(rq, p));
         BUG_ON(p->rt.nr_cpus_allowed <= 1);
 
-        BUG_ON(!p->se.on_rq);
+        BUG_ON(!p->on_rq);
         BUG_ON(!rt_task(p));
 
         return p;
@@ -1467,7 +1467,7 @@ static int pull_rt_task(struct rq *this_rq)
                  */
                 if (p && (p->prio < this_rq->rt.highest_prio.curr)) {
                         WARN_ON(p == src_rq->curr);
-                        WARN_ON(!p->se.on_rq);
+                        WARN_ON(!p->on_rq);
 
                         /*
                          * There's a chance that p is higher in priority
@@ -1538,7 +1538,7 @@ static void set_cpus_allowed_rt(struct task_struct *p,
          * Update the migration status of the RQ if we have an RT task
          * which is running AND changing its weight value.
          */
-        if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) {
+        if (p->on_rq && (weight != p->rt.nr_cpus_allowed)) {
                 struct rq *rq = task_rq(p);
 
                 if (!task_current(rq, p)) {
@@ -1608,7 +1608,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p)
          * we may need to handle the pulling of RT tasks
          * now.
          */
-        if (p->se.on_rq && !rq->rt.rt_nr_running)
+        if (p->on_rq && !rq->rt.rt_nr_running)
                 pull_rt_task(rq);
 }
 
@@ -1638,7 +1638,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
          * If that current running task is also an RT task
          * then see if we can move to another run queue.
          */
-        if (p->se.on_rq && rq->curr != p) {
+        if (p->on_rq && rq->curr != p) {
 #ifdef CONFIG_SMP
                 if (rq->rt.overloaded && push_rt_task(rq) &&
                     /* Don't resched if we changed runqueues */
@@ -1657,7 +1657,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 static void
 prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
 {
-        if (!p->se.on_rq)
+        if (!p->on_rq)
                 return;
 
         if (rq->curr == p) {
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index 1ba2bd40fdac..f607de42e6fc 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -26,7 +26,7 @@ static struct task_struct *pick_next_task_stop(struct rq *rq)
 {
         struct task_struct *stop = rq->stop;
 
-        if (stop && stop->se.on_rq)
+        if (stop && stop->on_rq)
                 return stop;
 
         return NULL;