posix timers: discard SI_TIMER signals on exec

Based on Roland's patch. This approach was suggested by Austin Clements
from the very beginning, and then by Linus.

As Austin pointed out, the execing task can be killed by SI_TIMER signal
because exec flushes the signal handlers, but doesn't discard the pending
signals generated by posix timers. Perhaps not a bug, but people find this
surprising. See http://bugzilla.kernel.org/show_bug.cgi?id=10460

Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Austin Clements <amdragon+kernelbugzilla@mit.edu>
Cc: Roland McGrath <roland@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 37 insertions, 0 deletions

diff --git a/fs/exec.c b/fs/exec.c
index 3c2ba7ce11d4..9448f1b50b4a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -860,6 +860,7 @@ static int de_thread(struct task_struct *tsk)
 
 no_thread_group:
         exit_itimers(sig);
+        flush_itimer_signals();
         if (leader)
                 release_task(leader);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5395a6176f4b..3e05e5474749 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1848,7 +1848,9 @@ extern void exit_thread(void);
 extern void exit_files(struct task_struct *);
 extern void __cleanup_signal(struct signal_struct *);
 extern void __cleanup_sighand(struct sighand_struct *);
+
 extern void exit_itimers(struct signal_struct *);
+extern void flush_itimer_signals(void);
 
 extern NORET_TYPE void do_group_exit(int);
 
diff --git a/kernel/signal.c b/kernel/signal.c
index 2955f6c4f36e..6c0958e52ea7 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -231,6 +231,40 @@ void flush_signals(struct task_struct *t)
         spin_unlock_irqrestore(&t->sighand->siglock, flags);
 }
 
+static void __flush_itimer_signals(struct sigpending *pending)
+{
+        sigset_t signal, retain;
+        struct sigqueue *q, *n;
+
+        signal = pending->signal;
+        sigemptyset(&retain);
+
+        list_for_each_entry_safe(q, n, &pending->list, list) {
+                int sig = q->info.si_signo;
+
+                if (likely(q->info.si_code != SI_TIMER)) {
+                        sigaddset(&retain, sig);
+                } else {
+                        sigdelset(&signal, sig);
+                        list_del_init(&q->list);
+                        __sigqueue_free(q);
+                }
+        }
+
+        sigorsets(&pending->signal, &signal, &retain);
+}
+
+void flush_itimer_signals(void)
+{
+        struct task_struct *tsk = current;
+        unsigned long flags;
+
+        spin_lock_irqsave(&tsk->sighand->siglock, flags);
+        __flush_itimer_signals(&tsk->pending);
+        __flush_itimer_signals(&tsk->signal->shared_pending);
+        spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
+}
+
 void ignore_signals(struct task_struct *t)
 {
         int i;