Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fix from Thomas Gleixner:
 "A single scheduler fix:

  Prevent idle task from ever being preempted. That makes sure that
  synchronize_rcu_tasks() which is ignoring idle task does not pretend
  that no task is stuck in preempted state. If that happens and idle was
  preempted on a ftrace trampoline the machine crashes due to
  inconsistent state"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/core: Call __schedule() from do_idle() without enabling preemption

3 files changed, 28 insertions, 1 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 759f4bd52cd6..803c3bc274c4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3502,6 +3502,31 @@ asmlinkage __visible void __sched schedule(void)
 }
 EXPORT_SYMBOL(schedule);
 
+/*
+ * synchronize_rcu_tasks() makes sure that no task is stuck in preempted
+ * state (have scheduled out non-voluntarily) by making sure that all
+ * tasks have either left the run queue or have gone into user space.
+ * As idle tasks do not do either, they must not ever be preempted
+ * (schedule out non-voluntarily).
+ *
+ * schedule_idle() is similar to schedule_preempt_disable() except that it
+ * never enables preemption because it does not call sched_submit_work().
+ */
+void __sched schedule_idle(void)
+{
+        /*
+         * As this skips calling sched_submit_work(), which the idle task does
+         * regardless because that function is a nop when the task is in a
+         * TASK_RUNNING state, make sure this isn't used someplace that the
+         * current task can be in any other state. Note, idle is always in the
+         * TASK_RUNNING state.
+         */
+        WARN_ON_ONCE(current->state);
+        do {
+                __schedule(false);
+        } while (need_resched());
+}
+
 #ifdef CONFIG_CONTEXT_TRACKING
 asmlinkage __visible void __sched schedule_user(void)
 {
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 2a25a9ec2c6e..ef63adce0c9c 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -265,7 +265,7 @@ static void do_idle(void)
         smp_mb__after_atomic();
 
         sched_ttwu_pending();
-        schedule_preempt_disabled();
+        schedule_idle();
 
         if (unlikely(klp_patch_pending(current)))
                 klp_update_patch_state(current);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7808ab050599..6dda2aab731e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1467,6 +1467,8 @@ static inline struct cpuidle_state *idle_get_state(struct rq *rq)
 }
 #endif
 
+extern void schedule_idle(void);
+
 extern void sysrq_sched_debug_show(void);
 extern void sched_init_granularity(void);
 extern void update_max_interval(void);