sched/fair: Use task_rcu_dereference()

Simplify task_numa_compare()'s task reference magic by using
task_rcu_dereference().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Kirill Tkhai <ktkhai@parallels.com>
Cc: Kirill Tkhai <tkhai@yandex.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Link: http://lkml.kernel.org/r/20160518195733.GA15914@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1e87bb6..c6dd8ba 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1305,6 +1305,8 @@ static void task_numa_assign(struct task_numa_env *env,
 {
        if (env->best_task)
                put_task_struct(env->best_task);
+       if (p)
+               get_task_struct(p);
 
        env->best_task = p;
        env->best_imp = imp;
@@ -1372,31 +1374,11 @@ static void task_numa_compare(struct task_numa_env *env,
        long imp = env->p->numa_group ? groupimp : taskimp;
        long moveimp = imp;
        int dist = env->dist;
-       bool assigned = false;
 
        rcu_read_lock();
-
-       raw_spin_lock_irq(&dst_rq->lock);
-       cur = dst_rq->curr;
-       /*
-        * No need to move the exiting task or idle task.
-        */
-       if ((cur->flags & PF_EXITING) || is_idle_task(cur))
+       cur = task_rcu_dereference(&dst_rq->curr);
+       if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur)))
                cur = NULL;
-       else {
-               /*
-                * The task_struct must be protected here to protect the
-                * p->numa_faults access in the task_weight since the
-                * numa_faults could already be freed in the following path:
-                * finish_task_switch()
-                *     --> put_task_struct()
-                *         --> __put_task_struct()
-                *             --> task_numa_free()
-                */
-               get_task_struct(cur);
-       }
-
-       raw_spin_unlock_irq(&dst_rq->lock);
 
        /*
         * Because we have preemption enabled we can get migrated around and
@@ -1479,7 +1461,6 @@ balance:
                 */
                if (!load_too_imbalanced(src_load, dst_load, env)) {
                        imp = moveimp - 1;
-                       put_task_struct(cur);
                        cur = NULL;
                        goto assign;
                }
@@ -1505,16 +1486,9 @@ balance:
                env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
 
 assign:
-       assigned = true;
        task_numa_assign(env, cur, imp);
 unlock:
        rcu_read_unlock();
-       /*
-        * The dst_rq->curr isn't assigned. The protection for task_struct is
-        * finished.
-        */
-       if (cur && !assigned)
-               put_task_struct(cur);
 }
 
 static void task_numa_find_cpu(struct task_numa_env *env,