summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorOleg Nesterov <oleg@tv-sign.ru>2008-06-08 21:20:41 +0400
committerIngo Molnar <mingo@elte.hu>2008-06-10 11:37:25 +0200
commit16882c1e962b4be5122fc05aaf2afc10fd9e2d15 (patch)
treec39cae4ae4874998d7e3486cd57d57613b05a89c
parent39b945a37bac2b692773a470890c8ba301485b15 (diff)
downloadlinux-16882c1e962b4be5122fc05aaf2afc10fd9e2d15.tar.gz
linux-16882c1e962b4be5122fc05aaf2afc10fd9e2d15.tar.bz2
linux-16882c1e962b4be5122fc05aaf2afc10fd9e2d15.zip
sched: 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. Hopefully it will have more users, that is why the task's state is passed separately. Note this "__TASK_STOPPED | __TASK_TRACED" check in signal_pending_state(). This is needed to preserve the current behaviour (ptrace_notify). I hope this check will be removed soon, but this (afaics good) change needs the separate discussion. The fast path is "(state & (INTERRUPTIBLE | WAKEKILL)) + signal_pending(p)", basically the same that schedule() does now. However, this patch of course bloats schedule(). Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Ingo Molnar <mingo@elte.hu>
-rw-r--r--include/linux/sched.h13
-rw-r--r--kernel/sched.c6
2 files changed, 15 insertions, 4 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ae0be3c62375..c5d3f847ca8d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2026,6 +2026,19 @@ static inline int fatal_signal_pending(struct task_struct *p)
return signal_pending(p) && __fatal_signal_pending(p);
}
+static inline 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_STOPPED | __TASK_TRACED))
+ return 0;
+
+ return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p);
+}
+
static inline int need_resched(void)
{
return unlikely(test_thread_flag(TIF_NEED_RESCHED));
diff --git a/kernel/sched.c b/kernel/sched.c
index bfb8ad8ed171..2c65bf29d133 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4159,12 +4159,10 @@ 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;
}