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

Pull scheduler fixes from Ingo Molnar:

 - Apply a number of membarrier related fixes and cleanups, which fixes
   a use-after-free race in the membarrier code

 - Introduce proper RCU protection for tasks on the runqueue - to get
   rid of the subtle task_rcu_dereference() interface that was easy to
   get wrong

 - Misc fixes, but also an EAS speedup

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Avoid redundant EAS calculation
  sched/core: Remove double update_max_interval() call on CPU startup
  sched/core: Fix preempt_schedule() interrupt return comment
  sched/fair: Fix -Wunused-but-set-variable warnings
  sched/core: Fix migration to invalid CPU in __set_cpus_allowed_ptr()
  sched/membarrier: Return -ENOMEM to userspace on memory allocation failure
  sched/membarrier: Skip IPIs when mm->mm_users == 1
  selftests, sched/membarrier: Add multi-threaded test
  sched/membarrier: Fix p->mm->membarrier_state racy load
  sched/membarrier: Call sync_core only before usermode for same mm
  sched/membarrier: Remove redundant check
  sched/membarrier: Fix private expedited registration check
  tasks, sched/core: RCUify the assignment of rq->curr
  tasks, sched/core: With a grace period after finish_task_switch(), remove unnecessary code
  tasks, sched/core: Ensure tasks are available for a grace period after leaving the runqueue
  tasks: Add a count of task RCU users
  sched/core: Convert vcpu_is_preempted() from macro to an inline function
  sched/fair: Remove unused cfs_rq_clock_task() function

1 files changed, 6 insertions, 68 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 22ab6a4bdc51..a46a50d67002 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -182,6 +182,11 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
 	put_task_struct(tsk);
 }
 
+void put_task_struct_rcu_user(struct task_struct *task)
+{
+	if (refcount_dec_and_test(&task->rcu_users))
+		call_rcu(&task->rcu, delayed_put_task_struct);
+}
 
 void release_task(struct task_struct *p)
 {
@@ -222,76 +227,13 @@ repeat:
 
 	write_unlock_irq(&tasklist_lock);
 	release_thread(p);
-	call_rcu(&p->rcu, delayed_put_task_struct);
+	put_task_struct_rcu_user(p);
 
 	p = leader;
 	if (unlikely(zap_leader))
 		goto repeat;
 }
 
-/*
- * Note that if this function returns a valid task_struct pointer (!NULL)
- * task->usage must remain >0 for the duration of the RCU critical section.
- */
-struct task_struct *task_rcu_dereference(struct task_struct **ptask)
-{
-	struct sighand_struct *sighand;
-	struct task_struct *task;
-
-	/*
-	 * We need to verify that release_task() was not called and thus
-	 * delayed_put_task_struct() can't run and drop the last reference
-	 * before rcu_read_unlock(). We check task->sighand != NULL,
-	 * but we can read the already freed and reused memory.
-	 */
-retry:
-	task = rcu_dereference(*ptask);
-	if (!task)
-		return NULL;
-
-	probe_kernel_address(&task->sighand, sighand);
-
-	/*
-	 * Pairs with atomic_dec_and_test() in put_task_struct(). If this task
-	 * was already freed we can not miss the preceding update of this
-	 * pointer.
-	 */
-	smp_rmb();
-	if (unlikely(task != READ_ONCE(*ptask)))
-		goto retry;
-
-	/*
-	 * We've re-checked that "task == *ptask", now we have two different
-	 * cases:
-	 *
-	 * 1. This is actually the same task/task_struct. In this case
-	 *    sighand != NULL tells us it is still alive.
-	 *
-	 * 2. This is another task which got the same memory for task_struct.
-	 *    We can't know this of course, and we can not trust
-	 *    sighand != NULL.
-	 *
-	 *    In this case we actually return a random value, but this is
-	 *    correct.
-	 *
-	 *    If we return NULL - we can pretend that we actually noticed that
-	 *    *ptask was updated when the previous task has exited. Or pretend
-	 *    that probe_slab_address(&sighand) reads NULL.
-	 *
-	 *    If we return the new task (because sighand is not NULL for any
-	 *    reason) - this is fine too. This (new) task can't go away before
-	 *    another gp pass.
-	 *
-	 *    And note: We could even eliminate the false positive if re-read
-	 *    task->sighand once again to avoid the falsely NULL. But this case
-	 *    is very unlikely so we don't care.
-	 */
-	if (!sighand)
-		return NULL;
-
-	return task;
-}
-
 void rcuwait_wake_up(struct rcuwait *w)
 {
 	struct task_struct *task;
@@ -311,10 +253,6 @@ void rcuwait_wake_up(struct rcuwait *w)
 	 */
 	smp_mb(); /* (B) */
 
-	/*
-	 * Avoid using task_rcu_dereference() magic as long as we are careful,
-	 * see comment in rcuwait_wait_event() regarding ->exit_state.
-	 */
 	task = rcu_dereference(w->task);
 	if (task)
 		wake_up_process(task);