6 files changed, 41 insertions, 27 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b33a700652dc..ff4e2f9c24a7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1067,8 +1067,7 @@ struct sched_class {
         void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
-        int  (*select_task_rq)(struct rq *rq, struct task_struct *p,
-                               int sd_flag, int flags);
+        int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
 
         void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
         void (*post_schedule) (struct rq *this_rq);
diff --git a/kernel/sched.c b/kernel/sched.c
index d398f2f0a3c9..d4b815d345b3 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2195,13 +2195,15 @@ static int migration_cpu_stop(void *data);
  * The task's runqueue lock must be held.
  * Returns true if you have to wait for migration thread.
  */
-static bool migrate_task(struct task_struct *p, struct rq *rq)
+static bool need_migrate_task(struct task_struct *p)
 {
         /*
          * If the task is not on a runqueue (and not running), then
          * the next wake-up will properly place the task.
          */
-        return p->on_rq || task_running(rq, p);
+        bool running = p->on_rq || p->on_cpu;
+        smp_rmb(); /* finish_lock_switch() */
+        return running;
 }
 
 /*
@@ -2376,9 +2378,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
  * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
  */
 static inline
-int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags)
+int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
 {
-        int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags);
+        int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
 
         /*
          * In order not to call set_task_cpu() on a blocking task we need
@@ -2533,7 +2535,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
                 en_flags |= ENQUEUE_WAKING;
         }
 
-        cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags);
+        cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
         if (cpu != orig_cpu)
                 set_task_cpu(p, cpu);
         __task_rq_unlock(rq);
@@ -2744,7 +2746,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
          * We set TASK_WAKING so that select_task_rq() can drop rq->lock
          * without people poking at ->cpus_allowed.
          */
-        cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0);
+        cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
         set_task_cpu(p, cpu);
 
         p->state = TASK_RUNNING;
@@ -3474,7 +3476,7 @@ void sched_exec(void)
         int dest_cpu;
 
         rq = task_rq_lock(p, &flags);
-        dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0);
+        dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0);
         if (dest_cpu == smp_processor_id())
                 goto unlock;
 
@@ -3482,7 +3484,7 @@ void sched_exec(void)
          * select_task_rq() can race against ->cpus_allowed
          */
         if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
-            likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) {
+            likely(cpu_active(dest_cpu)) && need_migrate_task(p)) {
                 struct migration_arg arg = { p, dest_cpu };
 
                 task_rq_unlock(rq, &flags);
@@ -5911,7 +5913,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
                 goto out;
 
         dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
-        if (migrate_task(p, rq)) {
+        if (need_migrate_task(p)) {
                 struct migration_arg arg = { p, dest_cpu };
                 /* Need help from migration thread: drop lock and wait. */
                 __task_rq_unlock(rq);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 4ee50f0af8d1..96b2c95ac356 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1657,7 +1657,7 @@ static int select_idle_sibling(struct task_struct *p, int target)
  * preempt must be disabled.
  */
 static int
-select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags)
+select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
 {
         struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
         int cpu = smp_processor_id();
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index a776a6396427..0a51882534ea 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -7,7 +7,7 @@
 
 #ifdef CONFIG_SMP
 static int
-select_task_rq_idle(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
+select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
 {
         return task_cpu(p); /* IDLE tasks as never migrated */
 }
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 9ca4f5f879c4..19ecb3127379 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -977,13 +977,23 @@ static void yield_task_rt(struct rq *rq)
 static int find_lowest_rq(struct task_struct *task);
 
 static int
-select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
+select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
 {
+        struct task_struct *curr;
+        struct rq *rq;
+        int cpu;
+
         if (sd_flag != SD_BALANCE_WAKE)
                 return smp_processor_id();
 
+        cpu = task_cpu(p);
+        rq = cpu_rq(cpu);
+
+        rcu_read_lock();
+        curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+
         /*
-         * If the current task is an RT task, then
+         * If the current task on @p's runqueue is an RT task, then
          * try to see if we can wake this RT task up on another
          * runqueue. Otherwise simply start this RT task
          * on its current runqueue.
@@ -997,21 +1007,25 @@ select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
          * lock?
          *
          * For equal prio tasks, we just let the scheduler sort it out.
+         *
+         * Otherwise, just let it ride on the affined RQ and the
+         * post-schedule router will push the preempted task away
+         *
+         * This test is optimistic, if we get it wrong the load-balancer
+         * will have to sort it out.
          */
-        if (unlikely(rt_task(rq->curr)) &&
-            (rq->curr->rt.nr_cpus_allowed < 2 ||
-             rq->curr->prio < p->prio) &&
+        if (curr && unlikely(rt_task(curr)) &&
+            (curr->rt.nr_cpus_allowed < 2 ||
+             curr->prio < p->prio) &&
             (p->rt.nr_cpus_allowed > 1)) {
-                int cpu = find_lowest_rq(p);
+                int target = find_lowest_rq(p);
 
-                return (cpu == -1) ? task_cpu(p) : cpu;
+                if (target != -1)
+                        cpu = target;
         }
+        rcu_read_unlock();
 
-        /*
-         * Otherwise, just let it ride on the affined RQ and the
-         * post-schedule router will push the preempted task away
-         */
-        return task_cpu(p);
+        return cpu;
 }
 
 static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index f607de42e6fc..6f437632afab 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -9,8 +9,7 @@
 
 #ifdef CONFIG_SMP
 static int
-select_task_rq_stop(struct rq *rq, struct task_struct *p,
-                    int sd_flag, int flags)
+select_task_rq_stop(struct task_struct *p, int sd_flag, int flags)
 {
         return task_cpu(p); /* stop tasks as never migrate */
 }