exit: Factor thread_group_exited out of pidfd_poll

Create an independent helper thread_group_exited which returns true
when all threads have passed exit_notify in do_exit.  AKA all of the
threads are at least zombies and might be dead or completely gone.

Create this helper by taking the logic out of pidfd_poll where it is
already tested, and adding a READ_ONCE on the read of
task->exit_state.

I will be changing the user mode driver code to use this same logic
to know when a user mode driver needs to be restarted.

Place the new helper thread_group_exited in kernel/exit.c and
EXPORT it so it can be used by modules.

Link: https://lkml.kernel.org/r/20200702164140.4468-13-ebiederm@xmission.com
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

3 files changed, 27 insertions, 5 deletions

diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 0ee5e696c5d8..1bad18a1d8ba 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -674,6 +674,8 @@ static inline int thread_group_empty(struct task_struct *p)
 #define delay_group_leader(p) \
 		(thread_group_leader(p) && !thread_group_empty(p))
 
+extern bool thread_group_exited(struct pid *pid);
+
 extern struct sighand_struct *__lock_task_sighand(struct task_struct *task,
 							unsigned long *flags);
 
diff --git a/kernel/exit.c b/kernel/exit.c
index d3294b611df1..dee246c0866f 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1713,6 +1713,30 @@ Efault:
 }
 #endif
 
+/**
+ * thread_group_exited - check that a thread group has exited
+ * @pid: tgid of thread group to be checked.
+ *
+ * Test if the thread group represented by tgid has exited (all
+ * threads are zombies, dead or completely gone).
+ *
+ * Return: true if the thread group has exited. false otherwise.
+ */
+bool thread_group_exited(struct pid *pid)
+{
+	struct task_struct *task;
+	bool exited;
+
+	rcu_read_lock();
+	task = pid_task(pid, PIDTYPE_PID);
+	exited = !task ||
+		(READ_ONCE(task->exit_state) && thread_group_empty(task));
+	rcu_read_unlock();
+
+	return exited;
+}
+EXPORT_SYMBOL(thread_group_exited);
+
 __weak void abort(void)
 {
 	BUG();
diff --git a/kernel/fork.c b/kernel/fork.c
index 142b23645d82..bf215af7a904 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1787,22 +1787,18 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
  */
 static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
 {
-	struct task_struct *task;
 	struct pid *pid = file->private_data;
 	__poll_t poll_flags = 0;
 
 	poll_wait(file, &pid->wait_pidfd, pts);
 
-	rcu_read_lock();
-	task = pid_task(pid, PIDTYPE_PID);
 	/*
 	 * Inform pollers only when the whole thread group exits.
 	 * If the thread group leader exits before all other threads in the
 	 * group, then poll(2) should block, similar to the wait(2) family.
 	 */
-	if (!task || (task->exit_state && thread_group_empty(task)))
+	if (thread_group_exited(pid))
 		poll_flags = EPOLLIN | EPOLLRDNORM;
-	rcu_read_unlock();
 
 	return poll_flags;
 }