[RFC PATCH] pidfd: implement PIDFD_THREAD flag for pidfd_open()

[Oleg Nesterov <oleg@redhat.com>]

On 01/27, Oleg Nesterov wrote:
>
> I'll (hopefully) send v2 on top of
>
> 	pidfd: cleanup the usage of __pidfd_prepare's flags
> 	pidfd: don't do_notify_pidfd() if !thread_group_empty()
>
> on Monday

Sorry, I don't have time to finish v2 today, I need to update the comments
and write the changelog.

But the patch itself is ready, I am sending it for review.

Tycho, Christian, any comments?

Oleg.


From c31780f6c1136a72048d24701ac6d8401fc1afda Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Sat, 27 Jan 2024 16:59:18 +0100
Subject: [PATCH] pidfd: implement PIDFD_THREAD flag for pidfd_open()

---
 include/uapi/linux/pidfd.h |  3 ++-
 kernel/exit.c              |  7 +++++++
 kernel/fork.c              | 29 +++++++++++++++++++++++++++--
 kernel/pid.c               |  2 +-
 kernel/signal.c            |  4 +++-
 5 files changed, 40 insertions(+), 5 deletions(-)

diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h
index 5406fbc13074..2e6461459877 100644
--- a/include/uapi/linux/pidfd.h
+++ b/include/uapi/linux/pidfd.h
@@ -7,6 +7,7 @@
 #include <linux/fcntl.h>
 
 /* Flags for pidfd_open().  */
-#define PIDFD_NONBLOCK O_NONBLOCK
+#define PIDFD_NONBLOCK	O_NONBLOCK
+#define PIDFD_THREAD	O_EXCL
 
 #endif /* _UAPI_LINUX_PIDFD_H */
diff --git a/kernel/exit.c b/kernel/exit.c
index dfb963d2f862..74fe6bfb9577 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -739,6 +739,13 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 		kill_orphaned_pgrp(tsk->group_leader, NULL);
 
 	tsk->exit_state = EXIT_ZOMBIE;
+	/*
+	 * sub-thread or delay_group_leader(), wake up the PIDFD_THREAD
+	 * waiters.
+	 */
+	if (!thread_group_empty(tsk))
+		do_notify_pidfd(tsk);
+
 	if (unlikely(tsk->ptrace)) {
 		int sig = thread_group_leader(tsk) &&
 				thread_group_empty(tsk) &&
diff --git a/kernel/fork.c b/kernel/fork.c
index 347641398f9d..977b58c0eac6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -101,6 +101,7 @@
 #include <linux/user_events.h>
 #include <linux/iommu.h>
 #include <linux/rseq.h>
+#include <uapi/linux/pidfd.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
@@ -2050,6 +2051,8 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
 
 	seq_put_decimal_ll(m, "Pid:\t", nr);
 
+	/* TODO: report PIDFD_THREAD */
+
 #ifdef CONFIG_PID_NS
 	seq_put_decimal_ll(m, "\nNSpid:\t", nr);
 	if (nr > 0) {
@@ -2068,12 +2071,27 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
 }
 #endif
 
+static bool pidfd_task_exited(struct pid *pid, bool thread)
+{
+	struct task_struct *task;
+	bool exited;
+
+	rcu_read_lock();
+	task = pid_task(pid, PIDTYPE_PID);
+	exited = !task ||
+		(READ_ONCE(task->exit_state) && (thread || thread_group_empty(task)));
+	rcu_read_unlock();
+
+	return exited;
+}
+
 /*
  * Poll support for process exit notification.
  */
 static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
 {
 	struct pid *pid = file->private_data;
+	bool thread = file->f_flags & PIDFD_THREAD;
 	__poll_t poll_flags = 0;
 
 	poll_wait(file, &pid->wait_pidfd, pts);
@@ -2083,7 +2101,7 @@ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
 	 * 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 (thread_group_exited(pid))
+	if (pidfd_task_exited(pid, thread))
 		poll_flags = EPOLLIN | EPOLLRDNORM;
 
 	return poll_flags;
@@ -2141,6 +2159,11 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
 		return PTR_ERR(pidfd_file);
 	}
 	get_pid(pid); /* held by pidfd_file now */
+	/*
+	 * anon_inode_getfile() ignores everything outside of the
+	 * O_ACCMODE | O_NONBLOCK mask, set PIDFD_THREAD manually.
+	 */
+	pidfd_file->f_flags |= (flags & PIDFD_THREAD);
 	*ret = pidfd_file;
 	return pidfd;
 }
@@ -2173,7 +2196,9 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
  */
 int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
 {
-	if (!pid || !pid_has_task(pid, PIDTYPE_TGID))
+	bool thread = flags & PIDFD_THREAD;
+
+	if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID));
 		return -EINVAL;
 
 	return __pidfd_prepare(pid, flags, ret);
diff --git a/kernel/pid.c b/kernel/pid.c
index c7a3e359f8f5..04bdd5ecf183 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -629,7 +629,7 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
 	int fd;
 	struct pid *p;
 
-	if (flags & ~PIDFD_NONBLOCK)
+	if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD))
 		return -EINVAL;
 
 	if (pid <= 0)
diff --git a/kernel/signal.c b/kernel/signal.c
index 9561a3962ca6..919cd33a0405 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2051,7 +2051,8 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 	WARN_ON_ONCE(!tsk->ptrace &&
 	       (tsk->group_leader != tsk || !thread_group_empty(tsk)));
 	/*
-	 * tsk is a group leader and has no threads, wake up the pidfd waiters.
+	 * tsk is a group leader and has no threads, wake up the !PIDFD_THREAD
+	 * waiters.
 	 */
 	if (thread_group_empty(tsk))
 		do_notify_pidfd(tsk);
@@ -3926,6 +3927,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 		prepare_kill_siginfo(sig, &kinfo);
 	}
 
+	/* TODO: respect PIDFD_THREAD */
 	ret = kill_pid_info(sig, &kinfo, pid);
 
 err:
-- 
2.25.1.362.g51ebf55