signal: Guarantee that SIGNAL_GROUP_EXIT is set on process exit

Track how many threads have not started exiting and when the last
thread starts exiting set SIGNAL_GROUP_EXIT.

This guarantees that SIGNAL_GROUP_EXIT will get set when a process
exits.  In practice this achieves nothing as glibc's implementation of
_exit calls sys_group_exit then sys_exit.  While glibc's implemenation
of pthread_exit calls exit (which cleansup and calls _exit) if it is
the last thread and sys_exit if it is the last thread.

This means the only way the kernel might observe a process that does
not set call exit_group is if the language runtime does not use glibc.

With more cleanups I hope to move the decrement of quick_threads
earlier.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: "Eric W. Biederman" <[email protected]>

Author: ebiederm

include/linux/sched/signal.h

@@ -94,6 +94,7 @@ struct signal_struct {
 	refcount_t		sigcnt;
 	atomic_t		live;
 	int			nr_threads;
+	int			quick_threads;
 	struct list_head	thread_head;
 
 	wait_queue_head_t	wait_chldexit;	/* for wait4() */

kernel/exit.c

@@ -733,11 +733,29 @@ static void check_stack_usage(void)
 static inline void check_stack_usage(void) {}
 #endif
 
+static void synchronize_group_exit(struct task_struct *tsk, long code)
+{
+	struct sighand_struct *sighand = tsk->sighand;
+	struct signal_struct *signal = tsk->signal;
+
+	spin_lock_irq(&sighand->siglock);
+	signal->quick_threads--;
+	if ((signal->quick_threads == 0) &&
+	    !(signal->flags & SIGNAL_GROUP_EXIT)) {
+		signal->flags = SIGNAL_GROUP_EXIT;
+		signal->group_exit_code = code;
+		signal->group_stop_count = 0;
+	}
+	spin_unlock_irq(&sighand->siglock);
+}
+
 void __noreturn do_exit(long code)
 {
 	struct task_struct *tsk = current;
 	int group_dead;
 
+	synchronize_group_exit(tsk, code);
+
 	WARN_ON(tsk->plug);
 
 	kcov_task_exit(tsk);

kernel/fork.c

@@ -1692,6 +1692,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 		return -ENOMEM;
 
 	sig->nr_threads = 1;
+	sig->quick_threads = 1;
 	atomic_set(&sig->live, 1);
 	refcount_set(&sig->sigcnt, 1);
 
@@ -2444,6 +2445,7 @@ static __latent_entropy struct task_struct *copy_process(
 			__this_cpu_inc(process_counts);
 		} else {
 			current->signal->nr_threads++;
+			current->signal->quick_threads++;
 			atomic_inc(&current->signal->live);
 			refcount_inc(&current->signal->sigcnt);
 			task_join_group_stop(p);