[PATCH] sched/core: simpler function for sched_exec migration

[cheng chao]

when sched_exec needs migration and CONFIG_PREEMPT_NONE=y,
migration_cpu_stop almost does nothing due to
the caller is !task_on_rq_queued().

currently CONFIG_PREEMPT and CONFIG_PREEMPT_VOLUNTARY work well because
the caller keeps task_on_rq_queued():

1. when CONFIG_PREEMPT=y
  stop_one_cpu
  ->cpu_stop_queue_work
    ->spin_unlock_irqrestore (preempt_enable calls __preempt_schedule)

2. when CONFIG_PREEMPT_VOLUNTARY=y
  stop_one_cpu
  ->wait_for_completion
    ->...
      -->might_sleep() (calls _cond_resched()

stop_one_cpu_sync is introduced here to address this problem,more further
it makes more simpler for CONFIG_PREEMPT=y or CONFIG_PREEMPT_VOLUNTARY=y
when sched_exec needs migration.

Signed-off-by: cheng chao <chengchao@xxxxxxxxxxx>
---
 include/linux/stop_machine.h |  1 +
 kernel/sched/core.c          |  2 +-
 kernel/stop_machine.c        | 21 +++++++++++++++++++++
 3 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 3cc9632..e4e7d42 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -28,6 +28,7 @@ struct cpu_stop_work {
 };
 
 int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg);
+void stop_one_cpu_sync(unsigned int cpu, cpu_stop_fn_t fn, void *arg);
 int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg);
 bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			 struct cpu_stop_work *work_buf);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 556cb07..2fd71e6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2958,7 +2958,7 @@ void sched_exec(void)
 		struct migration_arg arg = { p, dest_cpu };
 
 		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-		stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
+		stop_one_cpu_sync(task_cpu(p), migration_cpu_stop, &arg);
 		return;
 	}
 unlock:
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 4a1ca5f..24f8637 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -130,6 +130,27 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
 	return done.ret;
 }
 
+/**
+ * the caller keeps task_on_rq_queued, so it's more suitable for
+ * sched_exec on the case when needs migration
+ */
+void stop_one_cpu_sync(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
+{
+	struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = NULL };
+
+	if (!cpu_stop_queue_work(cpu, &work))
+		return;
+
+#if defined(CONFIG_PREEMPT_NONE) || defined(CONFIG_PREEMPT_VOLUNTARY)
+	/*
+	 * CONFIG_PREEMPT doesn't need call schedule here, because
+	 * preempt_enable already does the similar thing when call
+	 * cpu_stop_queue_work
+	 */
+	schedule();
+#endif
+}
+
 /* This controls the threads on each CPU. */
 enum multi_stop_state {
 	/* Dummy starting state for thread. */
-- 
2.4.11