.\" Copyright (c) 2019 by Michael Kerrisk <mtk.manpages@gmail.com>
.\"
.\" %%%LICENSE_START(VERBATIM)
.\" Permission is granted to make and distribute verbatim copies of this
.\" manual provided the copyright notice and this permission notice are
.\" preserved on all copies.
.\"
.\" Permission is granted to copy and distribute modified versions of this
.\" manual under the conditions for verbatim copying, provided that the
.\" entire resulting derived work is distributed under the terms of a
.\" permission notice identical to this one.
.\"
.\" Since the Linux kernel and libraries are constantly changing, this
.\" manual page may be incorrect or out-of-date.  The author(s) assume no
.\" responsibility for errors or omissions, or for damages resulting from
.\" the use of the information contained herein.  The author(s) may not
.\" have taken the same level of care in the production of this manual,
.\" which is licensed free of charge, as they might when working
.\" professionally.
.\"
.\" Formatted or processed versions of this manual, if unaccompanied by
.\" the source, must acknowledge the copyright and authors of this work.
.\" %%%LICENSE_END
.\"
.TH PIDFD_OPEN 2 2019-09-19 "Linux" "Linux Programmer's Manual"
.SH NAME
pidfd_open \- obtain a file descriptor that refers to a process
.SH SYNOPSIS
.nf
.B #include <sys/types.h>
.PP
.BI "int pidfd_open(pid_t " pid ", unsigned int " flags );
.fi
.SH DESCRIPTION
The
.BR pidfd_open ()
system call creates a file descriptor that refers to
the process whose PID is specified in
.IR pid .
The file descriptor is returned as the function result;
the close-on-exec flag is set on the file descriptor.
.PP
The
.I flags
argument is reserved for future use;
currently, this argument must be specified as 0.
.SH RETURN VALUE
On success,
.BR pidfd_open ()
returns a nonnegative file descriptor.
On error, \-1 is returned and
.I errno
is set to indicate the cause of the error.
.SH ERRORS
.TP
.B EINVAL
.I flags
is not 0.
.TP
.B EINVAL
.I pid
is not valid.
.TP
.B EMFILE
The per-process limit on the number of open file descriptors has been reached
(see the description of
.BR RLIMIT_NOFILE
in
.BR getrlimit (2)).
.TP
.B ENFILE
The system-wide limit on the total number of open files has been reached.
.TP
.B ENODEV
The anonymous inode filesystem is not available in this kernel.
.TP
.B ENOMEM
Insufficient kernel memory was available.
.TP
.B ESRCH
The process specified by
.I pid
does not exist.
.SH VERSIONS
.BR pidfd_open ()
first appeared in Linux 5.3.
.SH CONFORMING TO
.BR pidfd_open ()
is Linux specific.
.SH NOTES
Currently, there is no glibc wrapper for this system call; call it using
.BR syscall (2).
.PP
The following code sequence can be used to obtain a file descriptor
for the child of
.BR fork (2):
.PP
.in +4n
.EX
pid = fork();
if (pid > 0) {     /* If parent */
    pidfd = pidfd_open(pid, 0);
    ...
}
.EE
.in
.PP
Even if the child process has already terminated by the time of the
.BR pidfd_open ()
call, the returned file descriptor
is guaranteed to refer to the child because
the parent has not yet waited on the child
(and therefore, the child's ID has not been recycled).
.PP
The
.BR pidfd_send_signal (2)
system call can be used to send a signal to the process referred to by
a PID file descriptor.
.PP
A PID file descriptor can be monitored using
.BR poll (2),
.BR select (2),
and
.BR epoll (7).
When the process that it refers to terminates,
these interfaces indicate the file descriptor as readable.
Note, however, that in the current implementation,
nothing can be read from the file descriptor
.RB ( read (2)
on the file descriptor fails with the error
.BR EINVAL ).
.PP
The
.BR pidfd_open ()
system call is the preferred way of obtaining a PID file descriptor.
The alternative is to obtain a file descriptor by opening a
.I /proc/[pid]
directory.
However, the latter technique is possible only if the
.BR proc (5)
file system is mounted;
furthermore, the file descriptor obtained in this way is
.I not
pollable.
.PP
See also the discussion of the
.BR CLONE_PIDFD
flag in
.BR clone (2).
.SH EXAMPLE
The program below opens a PID file descriptor for the
process whose PID is specified as its command-line argument.
It then uses
.BR poll (2)
to monitor the file descriptor for process exit, as indicated by an
.BR EPOLLIN
event.
.\"
.SS Program source
\&
.nf
#define _GNU_SOURCE
#include <sys/types.h>
#include <sys/syscall.h>
#include <unistd.h>
#include <poll.h>
#include <stdlib.h>
#include <stdio.h>

#ifndef __NR_pidfd_open
#define __NR_pidfd_open 434   /* System call # on most architectures */
#endif

static int
pidfd_open(pid_t pid, unsigned int flags)
{
    return syscall(__NR_pidfd_open, pid, flags);
}

int
main(int argc, char *argv[])
{
    struct pollfd pollfd;
    int pidfd, ready;

    if (argc != 2) {
        fprintf(stderr, "Usage: %s <pid>\en", argv[0]);
        exit(EXIT_SUCCESS);
    }

    pidfd = pidfd_open(atoi(argv[1]), 0);
    if (pidfd == \-1) {
        perror("pidfd_open");
        exit(EXIT_FAILURE);
    }

    pollfd.fd = pidfd;
    pollfd.events = POLLIN;

    ready = poll(&pollfd, 1, \-1);
    if (ready == \-1) {
        perror("poll");
        exit(EXIT_FAILURE);
    }

    printf("Events (0x%x): POLLIN is %sset\en", pollfd.revents,
            (pollfd.revents & POLLIN) ? "" : "not ");

    exit(EXIT_SUCCESS);
}
.fi
.SH SEE ALSO
.BR clone (2),
.BR kill (2),
.BR pidfd_send_signal (2),
.BR poll (2),
.BR select (2),
.BR epoll (7)