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

Pull scheduler fix from Thomas Gleixner:
 "Fix a long standing state race in finish_task_switch()"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/core: Fix TASK_DEAD race in finish_task_switch()

2 files changed, 8 insertions, 7 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 615953141951..10a8faa1b0d4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2517,11 +2517,11 @@ static struct rq *finish_task_switch(struct task_struct *prev)
          * If a task dies, then it sets TASK_DEAD in tsk->state and calls
          * schedule one last time. The schedule call will never return, and
          * the scheduled task must drop that reference.
-         * The test for TASK_DEAD must occur while the runqueue locks are
-         * still held, otherwise prev could be scheduled on another cpu, die
-         * there before we look at prev->state, and then the reference would
-         * be dropped twice.
-         *              Manfred Spraul <manfred@colorfullife.com>
+         *
+         * We must observe prev->state before clearing prev->on_cpu (in
+         * finish_lock_switch), otherwise a concurrent wakeup can get prev
+         * running on another CPU and we could rave with its RUNNING -> DEAD
+         * transition, resulting in a double drop.
          */
         prev_state = prev->state;
         vtime_task_switch(prev);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 68cda117574c..6d2a119c7ad9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1078,9 +1078,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
          * After ->on_cpu is cleared, the task can be moved to a different CPU.
          * We must ensure this doesn't happen until the switch is completely
          * finished.
+         *
+         * Pairs with the control dependency and rmb in try_to_wake_up().
          */
-        smp_wmb();
-        prev->on_cpu = 0;
+        smp_store_release(&prev->on_cpu, 0);
 #endif
 #ifdef CONFIG_DEBUG_SPINLOCK
         /* this is a valid case when another task releases the spinlock */