schedule: fix TASK_WAKEKILL vs SIGKILL race

schedule() has the special "TASK_INTERRUPTIBLE && signal_pending()" case,
this allows us to do

	current->state = TASK_INTERRUPTIBLE;
	schedule();

without fear to sleep with pending signal.

However, the code like

	current->state = TASK_KILLABLE;
	schedule();

is not right, schedule() doesn't take TASK_WAKEKILL into account. This means
that mutex_lock_killable(), wait_for_completion_killable(), down_killable(),
schedule_timeout_killable() can miss SIGKILL (and btw the second SIGKILL has
no effect).

Introduce the new helper, signal_pending_state(), and change schedule() to
use it.

Note this "__TASK_STOPPED | __TASK_TRACED" check in signal_pending_state().
Probably it would be better to remove it, but this will change the current
behaviour and thus needs a separate discussion.

Note also that with or without this patch TASK_WAKEKILL is not exactly right
wrt /sbin/init, but this is another issue.

Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>

 include/linux/sched.h |    2 ++
 kernel/signal.c       |   14 ++++++++++++++
 kernel/sched.c        |    6 ++----
 3 files changed, 18 insertions(+), 4 deletions(-)

--- 26-rc2/include/linux/sched.h~1_SCHED_KILLABLE	2008-06-01 16:44:39.000000000 +0400
+++ 26-rc2/include/linux/sched.h	2008-06-01 16:44:39.000000000 +0400
@@ -2020,6 +2020,8 @@ static inline int signal_pending(struct 
 	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
 }
 
+extern int signal_pending_state(long state, struct task_struct *p);
+
 extern int __fatal_signal_pending(struct task_struct *p);
 
 static inline int fatal_signal_pending(struct task_struct *p)
--- 26-rc2/kernel/signal.c~1_SCHED_KILLABLE	2008-05-31 16:03:39.000000000 +0400
+++ 26-rc2/kernel/signal.c	2008-06-04 19:57:34.000000000 +0400
@@ -980,6 +980,20 @@ int __fatal_signal_pending(struct task_s
 }
 EXPORT_SYMBOL(__fatal_signal_pending);
 
+int signal_pending_state(long state, struct task_struct *p)
+{
+	if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL)))
+		return 0;
+	if (!signal_pending(p))
+		return 0;
+
+	if (state & TASK_INTERRUPTIBLE)
+		return 1;
+	if (state & (__TASK_STOPPED | __TASK_TRACED))
+		return 0;
+	return __fatal_signal_pending(p);
+}
+
 struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long *flags)
 {
 	struct sighand_struct *sighand;
--- 26-rc2/kernel/sched.c~1_SCHED_KILLABLE	2008-05-18 15:44:18.000000000 +0400
+++ 26-rc2/kernel/sched.c	2008-06-04 17:42:59.000000000 +0400
@@ -4510,12 +4510,10 @@ need_resched_nonpreemptible:
 	clear_tsk_need_resched(prev);
 
 	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
-		if (unlikely((prev->state & TASK_INTERRUPTIBLE) &&
-				signal_pending(prev))) {
+		if (unlikely(signal_pending_state(prev->state, prev)))
 			prev->state = TASK_RUNNING;
-		} else {
+		else
 			deactivate_task(rq, prev, 1);
-		}
 		switch_count = &prev->nvcsw;
 	}