fix group stop with exit race

do_signal_stop() counts all sub-thread and sets ->group_stop_count
accordingly.  Every thread should decrement ->group_stop_count and stop,
the last one should notify the parent.

However a sub-thread can exit before it notices the signal_pending(), or it
may be somewhere in do_exit() already.  In that case the group stop never
finishes properly.

Note: this is a minimal fix, we can add some optimizations later.  Say we
can return quickly if thread_group_empty().  Also, we can move some signal
related code from exit_notify() to exit_signals().

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

3 files changed, 28 insertions, 2 deletions

diff --git a/include/linux/signal.h b/include/linux/signal.h
index 7e095147656c..42d2e0a948f4 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -241,6 +241,7 @@ extern int show_unhandled_signals;
 
 struct pt_regs;
 extern int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka, struct pt_regs *regs, void *cookie);
+extern void exit_signals(struct task_struct *tsk);
 
 extern struct kmem_cache *sighand_cachep;
 
diff --git a/kernel/exit.c b/kernel/exit.c
index d7815f570882..8f3bf53a5b4d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -947,7 +947,7 @@ fastcall NORET_TYPE void do_exit(long code)
                 schedule();
         }
 
-        tsk->flags |= PF_EXITING;
+        exit_signals(tsk);  /* sets PF_EXITING */
         /*
          * tsk->flags are checked in the futex code to protect against
          * an exiting task cleaning up the robust pi futexes.
diff --git a/kernel/signal.c b/kernel/signal.c
index 3fca710a5cd7..209eec11eef5 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1739,7 +1739,7 @@ static int do_signal_stop(int signr)
                          * stop is always done with the siglock held,
                          * so this check has no races.
                          */
-                        if (!t->exit_state &&
+                        if (!(t->flags & PF_EXITING) &&
                             !task_is_stopped_or_traced(t)) {
                                 stop_count++;
                                 signal_wake_up(t, 0);
@@ -1900,6 +1900,31 @@ relock:
         return signr;
 }
 
+void exit_signals(struct task_struct *tsk)
+{
+        int group_stop = 0;
+
+        spin_lock_irq(&tsk->sighand->siglock);
+        if (unlikely(tsk->signal->group_stop_count) &&
+                        !--tsk->signal->group_stop_count) {
+                tsk->signal->flags = SIGNAL_STOP_STOPPED;
+                group_stop = 1;
+        }
+
+        /*
+         * From now this task is not visible for group-wide signals,
+         * see wants_signal(), do_signal_stop().
+         */
+        tsk->flags |= PF_EXITING;
+        spin_unlock_irq(&tsk->sighand->siglock);
+
+        if (unlikely(group_stop)) {
+                read_lock(&tasklist_lock);
+                do_notify_parent_cldstop(tsk, CLD_STOPPED);
+                read_unlock(&tasklist_lock);
+        }
+}
+
 EXPORT_SYMBOL(recalc_sigpending);
 EXPORT_SYMBOL_GPL(dequeue_signal);
 EXPORT_SYMBOL(flush_signals);