do_wait: fix the theoretical race with stop/trace/cont

do_wait:

	current->state = TASK_INTERRUPTIBLE;

	read_lock(&tasklist_lock);
	... search for the task to reap ...

In theory, the ->state changing can leak into the critical section.  Since
the child can change its status under read_lock(tasklist) in parallel
(finish_stop/ptrace_stop), we can miss the wakeup if __wake_up_parent()
sees us in TASK_RUNNING state.  Add the barrier.

Also, use __set_current_state() to set TASK_RUNNING.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Acked-by: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/kernel/exit.c b/kernel/exit.c
index dd83c841910121131a443afd3673a52b000917c0..7ef355dd3dca517ae74eaadf54f8ed50f7883290 100644 (file)
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1581,7 +1581,7 @@ repeat:
           (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type])))
                goto notask;
 
-       current->state = TASK_INTERRUPTIBLE;
+       set_current_state(TASK_INTERRUPTIBLE);
        read_lock(&tasklist_lock);
        tsk = current;
        do {
@@ -1608,7 +1608,7 @@ notask:
                }
        }
 end:
-       current->state = TASK_RUNNING;
+       __set_current_state(TASK_RUNNING);
        remove_wait_queue(&current->signal->wait_chldexit,&wait);
        if (wo->wo_info) {
                struct siginfo __user *infop = wo->wo_info;