1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
use crate::fmt;
use crate::io::{self, Error, ErrorKind};
use crate::mem;
use crate::num::NonZeroI32;
use crate::ptr;
use crate::sys;
use crate::sys::cvt;
use crate::sys::process::process_common::*;
use core::ffi::NonZero_c_int;

#[cfg(target_os = "linux")]
use crate::os::linux::process::PidFd;

#[cfg(target_os = "linux")]
use crate::sys::weak::raw_syscall;

#[cfg(any(
    target_os = "macos",
    target_os = "freebsd",
    all(target_os = "linux", target_env = "gnu"),
    all(target_os = "linux", target_env = "musl"),
))]
use crate::sys::weak::weak;

#[cfg(target_os = "vxworks")]
use libc::RTP_ID as pid_t;

#[cfg(not(target_os = "vxworks"))]
use libc::{c_int, pid_t};

#[cfg(not(any(target_os = "vxworks", target_os = "l4re")))]
use libc::{gid_t, uid_t};

////////////////////////////////////////////////////////////////////////////////
// Command
////////////////////////////////////////////////////////////////////////////////

impl Command {
    pub fn spawn(
        &mut self,
        default: Stdio,
        needs_stdin: bool,
    ) -> io::Result<(Process, StdioPipes)> {
        const CLOEXEC_MSG_FOOTER: [u8; 4] = *b"NOEX";

        let envp = self.capture_env();

        if self.saw_nul() {
            return Err(io::const_io_error!(
                ErrorKind::InvalidInput,
                "nul byte found in provided data",
            ));
        }

        let (ours, theirs) = self.setup_io(default, needs_stdin)?;

        if let Some(ret) = self.posix_spawn(&theirs, envp.as_ref())? {
            return Ok((ret, ours));
        }

        let (input, output) = sys::pipe::anon_pipe()?;

        // Whatever happens after the fork is almost for sure going to touch or
        // look at the environment in one way or another (PATH in `execvp` or
        // accessing the `environ` pointer ourselves). Make sure no other thread
        // is accessing the environment when we do the fork itself.
        //
        // Note that as soon as we're done with the fork there's no need to hold
        // a lock any more because the parent won't do anything and the child is
        // in its own process. Thus the parent drops the lock guard while the child
        // forgets it to avoid unlocking it on a new thread, which would be invalid.
        let env_lock = sys::os::env_read_lock();
        let (pid, pidfd) = unsafe { self.do_fork()? };

        if pid == 0 {
            crate::panic::always_abort();
            mem::forget(env_lock);
            drop(input);
            let Err(err) = unsafe { self.do_exec(theirs, envp.as_ref()) };
            let errno = err.raw_os_error().unwrap_or(libc::EINVAL) as u32;
            let errno = errno.to_be_bytes();
            let bytes = [
                errno[0],
                errno[1],
                errno[2],
                errno[3],
                CLOEXEC_MSG_FOOTER[0],
                CLOEXEC_MSG_FOOTER[1],
                CLOEXEC_MSG_FOOTER[2],
                CLOEXEC_MSG_FOOTER[3],
            ];
            // pipe I/O up to PIPE_BUF bytes should be atomic, and then
            // we want to be sure we *don't* run at_exit destructors as
            // we're being torn down regardless
            rtassert!(output.write(&bytes).is_ok());
            unsafe { libc::_exit(1) }
        }

        drop(env_lock);
        drop(output);

        // Safety: We obtained the pidfd from calling `clone3` with
        // `CLONE_PIDFD` so it's valid an otherwise unowned.
        let mut p = unsafe { Process::new(pid, pidfd) };
        let mut bytes = [0; 8];

        // loop to handle EINTR
        loop {
            match input.read(&mut bytes) {
                Ok(0) => return Ok((p, ours)),
                Ok(8) => {
                    let (errno, footer) = bytes.split_at(4);
                    assert_eq!(
                        CLOEXEC_MSG_FOOTER, footer,
                        "Validation on the CLOEXEC pipe failed: {:?}",
                        bytes
                    );
                    let errno = i32::from_be_bytes(errno.try_into().unwrap());
                    assert!(p.wait().is_ok(), "wait() should either return Ok or panic");
                    return Err(Error::from_raw_os_error(errno));
                }
                Err(ref e) if e.kind() == ErrorKind::Interrupted => {}
                Err(e) => {
                    assert!(p.wait().is_ok(), "wait() should either return Ok or panic");
                    panic!("the CLOEXEC pipe failed: {e:?}")
                }
                Ok(..) => {
                    // pipe I/O up to PIPE_BUF bytes should be atomic
                    assert!(p.wait().is_ok(), "wait() should either return Ok or panic");
                    panic!("short read on the CLOEXEC pipe")
                }
            }
        }
    }

    // Attempts to fork the process. If successful, returns Ok((0, -1))
    // in the child, and Ok((child_pid, -1)) in the parent.
    #[cfg(not(target_os = "linux"))]
    unsafe fn do_fork(&mut self) -> Result<(pid_t, pid_t), io::Error> {
        cvt(libc::fork()).map(|res| (res, -1))
    }

    // Attempts to fork the process. If successful, returns Ok((0, -1))
    // in the child, and Ok((child_pid, child_pidfd)) in the parent.
    #[cfg(target_os = "linux")]
    unsafe fn do_fork(&mut self) -> Result<(pid_t, pid_t), io::Error> {
        use crate::sync::atomic::{AtomicBool, Ordering};

        static HAS_CLONE3: AtomicBool = AtomicBool::new(true);
        const CLONE_PIDFD: u64 = 0x00001000;

        #[repr(C)]
        struct clone_args {
            flags: u64,
            pidfd: u64,
            child_tid: u64,
            parent_tid: u64,
            exit_signal: u64,
            stack: u64,
            stack_size: u64,
            tls: u64,
            set_tid: u64,
            set_tid_size: u64,
            cgroup: u64,
        }

        raw_syscall! {
            fn clone3(cl_args: *mut clone_args, len: libc::size_t) -> libc::c_long
        }

        // Bypassing libc for `clone3` can make further libc calls unsafe,
        // so we use it sparingly for now. See #89522 for details.
        // Some tools (e.g. sandboxing tools) may also expect `fork`
        // rather than `clone3`.
        let want_clone3_pidfd = self.get_create_pidfd();

        // If we fail to create a pidfd for any reason, this will
        // stay as -1, which indicates an error.
        let mut pidfd: pid_t = -1;

        // Attempt to use the `clone3` syscall, which supports more arguments
        // (in particular, the ability to create a pidfd). If this fails,
        // we will fall through this block to a call to `fork()`
        if want_clone3_pidfd && HAS_CLONE3.load(Ordering::Relaxed) {
            let mut args = clone_args {
                flags: CLONE_PIDFD,
                pidfd: &mut pidfd as *mut pid_t as u64,
                child_tid: 0,
                parent_tid: 0,
                exit_signal: libc::SIGCHLD as u64,
                stack: 0,
                stack_size: 0,
                tls: 0,
                set_tid: 0,
                set_tid_size: 0,
                cgroup: 0,
            };

            let args_ptr = &mut args as *mut clone_args;
            let args_size = crate::mem::size_of::<clone_args>();

            let res = cvt(clone3(args_ptr, args_size));
            match res {
                Ok(n) => return Ok((n as pid_t, pidfd)),
                Err(e) => match e.raw_os_error() {
                    // Multiple threads can race to execute this store,
                    // but that's fine - that just means that multiple threads
                    // will have tried and failed to execute the same syscall,
                    // with no other side effects.
                    Some(libc::ENOSYS) => HAS_CLONE3.store(false, Ordering::Relaxed),
                    // Fallback to fork if `EPERM` is returned. (e.g. blocked by seccomp)
                    Some(libc::EPERM) => {}
                    _ => return Err(e),
                },
            }
        }

        // Generally, we just call `fork`. If we get here after wanting `clone3`,
        // then the syscall does not exist or we do not have permission to call it.
        cvt(libc::fork()).map(|res| (res, pidfd))
    }

    pub fn exec(&mut self, default: Stdio) -> io::Error {
        let envp = self.capture_env();

        if self.saw_nul() {
            return io::const_io_error!(ErrorKind::InvalidInput, "nul byte found in provided data",);
        }

        match self.setup_io(default, true) {
            Ok((_, theirs)) => {
                unsafe {
                    // Similar to when forking, we want to ensure that access to
                    // the environment is synchronized, so make sure to grab the
                    // environment lock before we try to exec.
                    let _lock = sys::os::env_read_lock();

                    let Err(e) = self.do_exec(theirs, envp.as_ref());
                    e
                }
            }
            Err(e) => e,
        }
    }

    // And at this point we've reached a special time in the life of the
    // child. The child must now be considered hamstrung and unable to
    // do anything other than syscalls really. Consider the following
    // scenario:
    //
    //      1. Thread A of process 1 grabs the malloc() mutex
    //      2. Thread B of process 1 forks(), creating thread C
    //      3. Thread C of process 2 then attempts to malloc()
    //      4. The memory of process 2 is the same as the memory of
    //         process 1, so the mutex is locked.
    //
    // This situation looks a lot like deadlock, right? It turns out
    // that this is what pthread_atfork() takes care of, which is
    // presumably implemented across platforms. The first thing that
    // threads to *before* forking is to do things like grab the malloc
    // mutex, and then after the fork they unlock it.
    //
    // Despite this information, libnative's spawn has been witnessed to
    // deadlock on both macOS and FreeBSD. I'm not entirely sure why, but
    // all collected backtraces point at malloc/free traffic in the
    // child spawned process.
    //
    // For this reason, the block of code below should contain 0
    // invocations of either malloc of free (or their related friends).
    //
    // As an example of not having malloc/free traffic, we don't close
    // this file descriptor by dropping the FileDesc (which contains an
    // allocation). Instead we just close it manually. This will never
    // have the drop glue anyway because this code never returns (the
    // child will either exec() or invoke libc::exit)
    unsafe fn do_exec(
        &mut self,
        stdio: ChildPipes,
        maybe_envp: Option<&CStringArray>,
    ) -> Result<!, io::Error> {
        use crate::sys::{self, cvt_r};

        if let Some(fd) = stdio.stdin.fd() {
            cvt_r(|| libc::dup2(fd, libc::STDIN_FILENO))?;
        }
        if let Some(fd) = stdio.stdout.fd() {
            cvt_r(|| libc::dup2(fd, libc::STDOUT_FILENO))?;
        }
        if let Some(fd) = stdio.stderr.fd() {
            cvt_r(|| libc::dup2(fd, libc::STDERR_FILENO))?;
        }

        #[cfg(not(target_os = "l4re"))]
        {
            if let Some(_g) = self.get_groups() {
                //FIXME: Redox kernel does not support setgroups yet
                #[cfg(not(target_os = "redox"))]
                cvt(libc::setgroups(_g.len().try_into().unwrap(), _g.as_ptr()))?;
            }
            if let Some(u) = self.get_gid() {
                cvt(libc::setgid(u as gid_t))?;
            }
            if let Some(u) = self.get_uid() {
                // When dropping privileges from root, the `setgroups` call
                // will remove any extraneous groups. We only drop groups
                // if the current uid is 0 and we weren't given an explicit
                // set of groups. If we don't call this, then even though our
                // uid has dropped, we may still have groups that enable us to
                // do super-user things.
                //FIXME: Redox kernel does not support setgroups yet
                #[cfg(not(target_os = "redox"))]
                if libc::getuid() == 0 && self.get_groups().is_none() {
                    cvt(libc::setgroups(0, ptr::null()))?;
                }
                cvt(libc::setuid(u as uid_t))?;
            }
        }
        if let Some(ref cwd) = *self.get_cwd() {
            cvt(libc::chdir(cwd.as_ptr()))?;
        }

        if let Some(pgroup) = self.get_pgroup() {
            cvt(libc::setpgid(0, pgroup))?;
        }

        // emscripten has no signal support.
        #[cfg(not(target_os = "emscripten"))]
        {
            use crate::mem::MaybeUninit;
            use crate::sys::cvt_nz;
            // Reset signal handling so the child process starts in a
            // standardized state. libstd ignores SIGPIPE, and signal-handling
            // libraries often set a mask. Child processes inherit ignored
            // signals and the signal mask from their parent, but most
            // UNIX programs do not reset these things on their own, so we
            // need to clean things up now to avoid confusing the program
            // we're about to run.
            let mut set = MaybeUninit::<libc::sigset_t>::uninit();
            cvt(sigemptyset(set.as_mut_ptr()))?;
            cvt_nz(libc::pthread_sigmask(libc::SIG_SETMASK, set.as_ptr(), ptr::null_mut()))?;

            #[cfg(target_os = "android")] // see issue #88585
            {
                let mut action: libc::sigaction = mem::zeroed();
                action.sa_sigaction = libc::SIG_DFL;
                cvt(libc::sigaction(libc::SIGPIPE, &action, ptr::null_mut()))?;
            }
            #[cfg(not(target_os = "android"))]
            {
                let ret = sys::signal(libc::SIGPIPE, libc::SIG_DFL);
                if ret == libc::SIG_ERR {
                    return Err(io::Error::last_os_error());
                }
            }
        }

        for callback in self.get_closures().iter_mut() {
            callback()?;
        }

        // Although we're performing an exec here we may also return with an
        // error from this function (without actually exec'ing) in which case we
        // want to be sure to restore the global environment back to what it
        // once was, ensuring that our temporary override, when free'd, doesn't
        // corrupt our process's environment.
        let mut _reset = None;
        if let Some(envp) = maybe_envp {
            struct Reset(*const *const libc::c_char);

            impl Drop for Reset {
                fn drop(&mut self) {
                    unsafe {
                        *sys::os::environ() = self.0;
                    }
                }
            }

            _reset = Some(Reset(*sys::os::environ()));
            *sys::os::environ() = envp.as_ptr();
        }

        libc::execvp(self.get_program_cstr().as_ptr(), self.get_argv().as_ptr());
        Err(io::Error::last_os_error())
    }

    #[cfg(not(any(
        target_os = "macos",
        target_os = "freebsd",
        all(target_os = "linux", target_env = "gnu"),
        all(target_os = "linux", target_env = "musl"),
    )))]
    fn posix_spawn(
        &mut self,
        _: &ChildPipes,
        _: Option<&CStringArray>,
    ) -> io::Result<Option<Process>> {
        Ok(None)
    }

    // Only support platforms for which posix_spawn() can return ENOENT
    // directly.
    #[cfg(any(
        target_os = "macos",
        target_os = "freebsd",
        all(target_os = "linux", target_env = "gnu"),
        all(target_os = "linux", target_env = "musl"),
    ))]
    fn posix_spawn(
        &mut self,
        stdio: &ChildPipes,
        envp: Option<&CStringArray>,
    ) -> io::Result<Option<Process>> {
        use crate::mem::MaybeUninit;
        use crate::sys::{self, cvt_nz};

        if self.get_gid().is_some()
            || self.get_uid().is_some()
            || (self.env_saw_path() && !self.program_is_path())
            || !self.get_closures().is_empty()
            || self.get_groups().is_some()
            || self.get_create_pidfd()
        {
            return Ok(None);
        }

        // Only glibc 2.24+ posix_spawn() supports returning ENOENT directly.
        #[cfg(all(target_os = "linux", target_env = "gnu"))]
        {
            if let Some(version) = sys::os::glibc_version() {
                if version < (2, 24) {
                    return Ok(None);
                }
            } else {
                return Ok(None);
            }
        }

        // Solaris, glibc 2.29+, and musl 1.24+ can set a new working directory,
        // and maybe others will gain this non-POSIX function too. We'll check
        // for this weak symbol as soon as it's needed, so we can return early
        // otherwise to do a manual chdir before exec.
        weak! {
            fn posix_spawn_file_actions_addchdir_np(
                *mut libc::posix_spawn_file_actions_t,
                *const libc::c_char
            ) -> libc::c_int
        }
        let addchdir = match self.get_cwd() {
            Some(cwd) => {
                if cfg!(target_os = "macos") {
                    // There is a bug in macOS where a relative executable
                    // path like "../myprogram" will cause `posix_spawn` to
                    // successfully launch the program, but erroneously return
                    // ENOENT when used with posix_spawn_file_actions_addchdir_np
                    // which was introduced in macOS 10.15.
                    return Ok(None);
                }
                match posix_spawn_file_actions_addchdir_np.get() {
                    Some(f) => Some((f, cwd)),
                    None => return Ok(None),
                }
            }
            None => None,
        };

        let pgroup = self.get_pgroup();

        // Safety: -1 indicates we don't have a pidfd.
        let mut p = unsafe { Process::new(0, -1) };

        struct PosixSpawnFileActions<'a>(&'a mut MaybeUninit<libc::posix_spawn_file_actions_t>);

        impl Drop for PosixSpawnFileActions<'_> {
            fn drop(&mut self) {
                unsafe {
                    libc::posix_spawn_file_actions_destroy(self.0.as_mut_ptr());
                }
            }
        }

        struct PosixSpawnattr<'a>(&'a mut MaybeUninit<libc::posix_spawnattr_t>);

        impl Drop for PosixSpawnattr<'_> {
            fn drop(&mut self) {
                unsafe {
                    libc::posix_spawnattr_destroy(self.0.as_mut_ptr());
                }
            }
        }

        unsafe {
            let mut attrs = MaybeUninit::uninit();
            cvt_nz(libc::posix_spawnattr_init(attrs.as_mut_ptr()))?;
            let attrs = PosixSpawnattr(&mut attrs);

            let mut flags = 0;

            let mut file_actions = MaybeUninit::uninit();
            cvt_nz(libc::posix_spawn_file_actions_init(file_actions.as_mut_ptr()))?;
            let file_actions = PosixSpawnFileActions(&mut file_actions);

            if let Some(fd) = stdio.stdin.fd() {
                cvt_nz(libc::posix_spawn_file_actions_adddup2(
                    file_actions.0.as_mut_ptr(),
                    fd,
                    libc::STDIN_FILENO,
                ))?;
            }
            if let Some(fd) = stdio.stdout.fd() {
                cvt_nz(libc::posix_spawn_file_actions_adddup2(
                    file_actions.0.as_mut_ptr(),
                    fd,
                    libc::STDOUT_FILENO,
                ))?;
            }
            if let Some(fd) = stdio.stderr.fd() {
                cvt_nz(libc::posix_spawn_file_actions_adddup2(
                    file_actions.0.as_mut_ptr(),
                    fd,
                    libc::STDERR_FILENO,
                ))?;
            }
            if let Some((f, cwd)) = addchdir {
                cvt_nz(f(file_actions.0.as_mut_ptr(), cwd.as_ptr()))?;
            }

            if let Some(pgroup) = pgroup {
                flags |= libc::POSIX_SPAWN_SETPGROUP;
                cvt_nz(libc::posix_spawnattr_setpgroup(attrs.0.as_mut_ptr(), pgroup))?;
            }

            let mut set = MaybeUninit::<libc::sigset_t>::uninit();
            cvt(sigemptyset(set.as_mut_ptr()))?;
            cvt_nz(libc::posix_spawnattr_setsigmask(attrs.0.as_mut_ptr(), set.as_ptr()))?;
            cvt(sigaddset(set.as_mut_ptr(), libc::SIGPIPE))?;
            cvt_nz(libc::posix_spawnattr_setsigdefault(attrs.0.as_mut_ptr(), set.as_ptr()))?;

            flags |= libc::POSIX_SPAWN_SETSIGDEF | libc::POSIX_SPAWN_SETSIGMASK;
            cvt_nz(libc::posix_spawnattr_setflags(attrs.0.as_mut_ptr(), flags as _))?;

            // Make sure we synchronize access to the global `environ` resource
            let _env_lock = sys::os::env_read_lock();
            let envp = envp.map(|c| c.as_ptr()).unwrap_or_else(|| *sys::os::environ() as *const _);
            cvt_nz(libc::posix_spawnp(
                &mut p.pid,
                self.get_program_cstr().as_ptr(),
                file_actions.0.as_ptr(),
                attrs.0.as_ptr(),
                self.get_argv().as_ptr() as *const _,
                envp as *const _,
            ))?;
            Ok(Some(p))
        }
    }
}

////////////////////////////////////////////////////////////////////////////////
// Processes
////////////////////////////////////////////////////////////////////////////////

/// The unique ID of the process (this should never be negative).
pub struct Process {
    pid: pid_t,
    status: Option<ExitStatus>,
    // On Linux, stores the pidfd created for this child.
    // This is None if the user did not request pidfd creation,
    // or if the pidfd could not be created for some reason
    // (e.g. the `clone3` syscall was not available).
    #[cfg(target_os = "linux")]
    pidfd: Option<PidFd>,
}

impl Process {
    #[cfg(target_os = "linux")]
    unsafe fn new(pid: pid_t, pidfd: pid_t) -> Self {
        use crate::os::unix::io::FromRawFd;
        use crate::sys_common::FromInner;
        // Safety: If `pidfd` is nonnegative, we assume it's valid and otherwise unowned.
        let pidfd = (pidfd >= 0).then(|| PidFd::from_inner(sys::fd::FileDesc::from_raw_fd(pidfd)));
        Process { pid, status: None, pidfd }
    }

    #[cfg(not(target_os = "linux"))]
    unsafe fn new(pid: pid_t, _pidfd: pid_t) -> Self {
        Process { pid, status: None }
    }

    pub fn id(&self) -> u32 {
        self.pid as u32
    }

    pub fn kill(&mut self) -> io::Result<()> {
        // If we've already waited on this process then the pid can be recycled
        // and used for another process, and we probably shouldn't be killing
        // random processes, so just return an error.
        if self.status.is_some() {
            Err(io::const_io_error!(
                ErrorKind::InvalidInput,
                "invalid argument: can't kill an exited process",
            ))
        } else {
            cvt(unsafe { libc::kill(self.pid, libc::SIGKILL) }).map(drop)
        }
    }

    pub fn wait(&mut self) -> io::Result<ExitStatus> {
        use crate::sys::cvt_r;
        if let Some(status) = self.status {
            return Ok(status);
        }
        let mut status = 0 as c_int;
        cvt_r(|| unsafe { libc::waitpid(self.pid, &mut status, 0) })?;
        self.status = Some(ExitStatus::new(status));
        Ok(ExitStatus::new(status))
    }

    pub fn try_wait(&mut self) -> io::Result<Option<ExitStatus>> {
        if let Some(status) = self.status {
            return Ok(Some(status));
        }
        let mut status = 0 as c_int;
        let pid = cvt(unsafe { libc::waitpid(self.pid, &mut status, libc::WNOHANG) })?;
        if pid == 0 {
            Ok(None)
        } else {
            self.status = Some(ExitStatus::new(status));
            Ok(Some(ExitStatus::new(status)))
        }
    }
}

/// Unix exit statuses
//
// This is not actually an "exit status" in Unix terminology.  Rather, it is a "wait status".
// See the discussion in comments and doc comments for `std::process::ExitStatus`.
#[derive(PartialEq, Eq, Clone, Copy)]
pub struct ExitStatus(c_int);

impl fmt::Debug for ExitStatus {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        f.debug_tuple("unix_wait_status").field(&self.0).finish()
    }
}

impl ExitStatus {
    pub fn new(status: c_int) -> ExitStatus {
        ExitStatus(status)
    }

    fn exited(&self) -> bool {
        libc::WIFEXITED(self.0)
    }

    pub fn exit_ok(&self) -> Result<(), ExitStatusError> {
        // This assumes that WIFEXITED(status) && WEXITSTATUS==0 corresponds to status==0.  This is
        // true on all actual versions of Unix, is widely assumed, and is specified in SuS
        // https://pubs.opengroup.org/onlinepubs/9699919799/functions/wait.html .  If it is not
        // true for a platform pretending to be Unix, the tests (our doctests, and also
        // procsss_unix/tests.rs) will spot it.  `ExitStatusError::code` assumes this too.
        match NonZero_c_int::try_from(self.0) {
            /* was nonzero */ Ok(failure) => Err(ExitStatusError(failure)),
            /* was zero, couldn't convert */ Err(_) => Ok(()),
        }
    }

    pub fn code(&self) -> Option<i32> {
        self.exited().then(|| libc::WEXITSTATUS(self.0))
    }

    pub fn signal(&self) -> Option<i32> {
        libc::WIFSIGNALED(self.0).then(|| libc::WTERMSIG(self.0))
    }

    pub fn core_dumped(&self) -> bool {
        libc::WIFSIGNALED(self.0) && libc::WCOREDUMP(self.0)
    }

    pub fn stopped_signal(&self) -> Option<i32> {
        libc::WIFSTOPPED(self.0).then(|| libc::WSTOPSIG(self.0))
    }

    pub fn continued(&self) -> bool {
        libc::WIFCONTINUED(self.0)
    }

    pub fn into_raw(&self) -> c_int {
        self.0
    }
}

/// Converts a raw `c_int` to a type-safe `ExitStatus` by wrapping it without copying.
impl From<c_int> for ExitStatus {
    fn from(a: c_int) -> ExitStatus {
        ExitStatus(a)
    }
}

/// Convert a signal number to a readable, searchable name.
///
/// This string should be displayed right after the signal number.
/// If a signal is unrecognized, it returns the empty string, so that
/// you just get the number like "0". If it is recognized, you'll get
/// something like "9 (SIGKILL)".
fn signal_string(signal: i32) -> &'static str {
    match signal {
        libc::SIGHUP => " (SIGHUP)",
        libc::SIGINT => " (SIGINT)",
        libc::SIGQUIT => " (SIGQUIT)",
        libc::SIGILL => " (SIGILL)",
        libc::SIGTRAP => " (SIGTRAP)",
        libc::SIGABRT => " (SIGABRT)",
        libc::SIGBUS => " (SIGBUS)",
        libc::SIGFPE => " (SIGFPE)",
        libc::SIGKILL => " (SIGKILL)",
        libc::SIGUSR1 => " (SIGUSR1)",
        libc::SIGSEGV => " (SIGSEGV)",
        libc::SIGUSR2 => " (SIGUSR2)",
        libc::SIGPIPE => " (SIGPIPE)",
        libc::SIGALRM => " (SIGALRM)",
        libc::SIGTERM => " (SIGTERM)",
        libc::SIGCHLD => " (SIGCHLD)",
        libc::SIGCONT => " (SIGCONT)",
        libc::SIGSTOP => " (SIGSTOP)",
        libc::SIGTSTP => " (SIGTSTP)",
        libc::SIGTTIN => " (SIGTTIN)",
        libc::SIGTTOU => " (SIGTTOU)",
        libc::SIGURG => " (SIGURG)",
        libc::SIGXCPU => " (SIGXCPU)",
        libc::SIGXFSZ => " (SIGXFSZ)",
        libc::SIGVTALRM => " (SIGVTALRM)",
        libc::SIGPROF => " (SIGPROF)",
        libc::SIGWINCH => " (SIGWINCH)",
        #[cfg(not(target_os = "haiku"))]
        libc::SIGIO => " (SIGIO)",
        libc::SIGSYS => " (SIGSYS)",
        // For information on Linux signals, run `man 7 signal`
        #[cfg(all(
            target_os = "linux",
            any(
                target_arch = "x86_64",
                target_arch = "x86",
                target_arch = "arm",
                target_arch = "aarch64"
            )
        ))]
        libc::SIGSTKFLT => " (SIGSTKFLT)",
        #[cfg(target_os = "linux")]
        libc::SIGPWR => " (SIGPWR)",
        #[cfg(any(
            target_os = "macos",
            target_os = "ios",
            target_os = "tvos",
            target_os = "freebsd",
            target_os = "netbsd",
            target_os = "openbsd",
            target_os = "dragonfly"
        ))]
        libc::SIGEMT => " (SIGEMT)",
        #[cfg(any(
            target_os = "macos",
            target_os = "ios",
            target_os = "tvos",
            target_os = "freebsd",
            target_os = "netbsd",
            target_os = "openbsd",
            target_os = "dragonfly"
        ))]
        libc::SIGINFO => " (SIGINFO)",
        _ => "",
    }
}

impl fmt::Display for ExitStatus {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        if let Some(code) = self.code() {
            write!(f, "exit status: {code}")
        } else if let Some(signal) = self.signal() {
            let signal_string = signal_string(signal);
            if self.core_dumped() {
                write!(f, "signal: {signal}{signal_string} (core dumped)")
            } else {
                write!(f, "signal: {signal}{signal_string}")
            }
        } else if let Some(signal) = self.stopped_signal() {
            let signal_string = signal_string(signal);
            write!(f, "stopped (not terminated) by signal: {signal}{signal_string}")
        } else if self.continued() {
            write!(f, "continued (WIFCONTINUED)")
        } else {
            write!(f, "unrecognised wait status: {} {:#x}", self.0, self.0)
        }
    }
}

#[derive(PartialEq, Eq, Clone, Copy)]
pub struct ExitStatusError(NonZero_c_int);

impl Into<ExitStatus> for ExitStatusError {
    fn into(self) -> ExitStatus {
        ExitStatus(self.0.into())
    }
}

impl fmt::Debug for ExitStatusError {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        f.debug_tuple("unix_wait_status").field(&self.0).finish()
    }
}

impl ExitStatusError {
    pub fn code(self) -> Option<NonZeroI32> {
        ExitStatus(self.0.into()).code().map(|st| st.try_into().unwrap())
    }
}

#[cfg(target_os = "linux")]
#[unstable(feature = "linux_pidfd", issue = "82971")]
impl crate::os::linux::process::ChildExt for crate::process::Child {
    fn pidfd(&self) -> io::Result<&PidFd> {
        self.handle
            .pidfd
            .as_ref()
            .ok_or_else(|| Error::new(ErrorKind::Other, "No pidfd was created."))
    }

    fn take_pidfd(&mut self) -> io::Result<PidFd> {
        self.handle
            .pidfd
            .take()
            .ok_or_else(|| Error::new(ErrorKind::Other, "No pidfd was created."))
    }
}

#[cfg(test)]
#[path = "process_unix/tests.rs"]
mod tests;