pidfd: implement PIDFD_THREAD flag for pidfd_open()

With this flag:

	- pidfd_open() doesn't require that the target task must be
	  a thread-group leader

	- pidfd_poll() succeeds when the task exits and becomes a
	  zombie (iow, passes exit_notify()), even if it is a leader
	  and thread-group is not empty.

	  This means that the behaviour of pidfd_poll(PIDFD_THREAD,
	  pid-of-group-leader) is not well defined if it races with
	  exec() from its sub-thread; pidfd_poll() can succeed or not
	  depending on whether pidfd_task_exited() is called before
	  or after exchange_tids().

	  Perhaps we can improve this behaviour later, pidfd_poll()
	  can probably take sig->group_exec_task into account. But
	  this doesn't really differ from the case when the leader
	  exits before other threads (so pidfd_poll() succeeds) and
	  then another thread execs and pidfd_poll() will block again.

thread_group_exited() is no longer used, perhaps it can die.

Co-developed-by: Tycho Andersen <tycho@tycho.pizza>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20240131132602.GA23641@redhat.com
Tested-by: Tycho Andersen <tandersen@netflix.com>
Reviewed-by: Tycho Andersen <tandersen@netflix.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 31 insertions, 7 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 726a92043531f..1a9b910559169 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) {
@@ -2068,22 +2071,35 @@ 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);
-
 	/*
-	 * 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.
+	 * Depending on PIDFD_THREAD, inform pollers when the thread
+	 * or the whole thread-group exits.
 	 */
-	if (thread_group_exited(pid))
+	if (pidfd_task_exited(pid, thread))
 		poll_flags = EPOLLIN | EPOLLRDNORM;
 
 	return poll_flags;
@@ -2141,6 +2157,11 @@ 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;
 }
@@ -2154,7 +2175,8 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
  * Allocate a new file that stashes @pid and reserve a new pidfd number in the
  * caller's file descriptor table. The pidfd is reserved but not installed yet.
  *
- * The helper verifies that @pid is used as a thread group leader.
+ * The helper verifies that @pid is still in use, without PIDFD_THREAD the
+ * task identified by @pid must be a thread-group leader.
  *
  * If this function returns successfully the caller is responsible to either
  * call fd_install() passing the returned pidfd and pidfd file as arguments in
@@ -2173,7 +2195,9 @@ 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);