Background:
Over the last year, pidfd support was added to the Linux kernel. This
allows interacting with other processes. In particular, this allows
waiting on a child process with a timeout in a race-free way, bypassing
all of the awful signal-handler tricks that are usually required.
Pidfds can be obtained for a child process (as well as any other
process) via the `pidfd_open` syscall. Unfortunately, this requires
several conditions to hold in order to be race-free (i.e. the pid is not
reused).
Per `man pidfd_open`:
```
· the disposition of SIGCHLD has not been explicitly set to SIG_IGN
(see sigaction(2));
· the SA_NOCLDWAIT flag was not specified while establishing a han‐
dler for SIGCHLD or while setting the disposition of that signal to
SIG_DFL (see sigaction(2)); and
· the zombie process was not reaped elsewhere in the program (e.g.,
either by an asynchronously executed signal handler or by wait(2)
or similar in another thread).
If any of these conditions does not hold, then the child process
(along with a PID file descriptor that refers to it) should instead
be created using clone(2) with the CLONE_PIDFD flag.
```
Sadly, these conditions are impossible to guarantee once any libraries
are used. For example, C code runnng in a different thread could call
`wait()`, which is impossible to detect from Rust code trying to open a
pidfd.
While pid reuse issues should (hopefully) be rare in practice, we can do
better. By passing the `CLONE_PIDFD` flag to `clone()` or `clone3()`, we
can obtain a pidfd for the child process in a guaranteed race-free
manner.
This PR:
This PR adds Linux-specific process extension methods to allow obtaining
pidfds for processes spawned via the standard `Command` API. Other than
being made available to user code, the standard library does not make
use of these pidfds in any way. In particular, the implementation of
`Child::wait` is completely unchanged.
Two Linux-specific helper methods are added: `CommandExt::create_pidfd`
and `ChildExt::pidfd`. These methods are intended to serve as a building
block for libraries to build higher-level abstractions - in particular,
waiting on a process with a timeout.
I've included a basic test, which verifies that pidfds are created iff
the `create_pidfd` method is used. This test is somewhat special - it
should always succeed on systems with the `clone3` system call
available, and always fail on systems without `clone3` available. I'm
not sure how to best ensure this programatically.
This PR relies on the newer `clone3` system call to pass the `CLONE_FD`,
rather than the older `clone` system call. `clone3` was added to Linux
in the same release as pidfds, so this shouldn't unnecessarily limit the
kernel versions that this code supports.
Unresolved questions:
* What should the name of the feature gate be for these newly added
methods?
* Should the `pidfd` method distinguish between an error occurring
and `create_pidfd` not being called?
`weak!` is needed in a test in another module. With macros
1.0, importing `weak!` would require reordering module
declarations in `std/src/lib.rs`, which is a bit too
evil.
Provide ExitStatusError
Closes#73125
In MR #81452 "Add #[must_use] to [...] process::ExitStatus" we concluded that the existing arrangements in are too awkward so adding that `#[must_use]` is blocked on improving the ergonomics.
I wrote a mini-RFC-style discusion of the approach in https://github.com/rust-lang/rust/issues/73125#issuecomment-771092741
Closes#73125
This is in pursuance of
Issue #73127 Consider adding #[must_use] to std::process::ExitStatus
In
MR #81452 Add #[must_use] to [...] process::ExitStatus
we concluded that the existing arrangements in are too awkward
so adding that #[must_use] is blocked on improving the ergonomics.
I wrote a mini-RFC-style discusion of the approach in
https://github.com/rust-lang/rust/issues/73125#issuecomment-771092741
Signed-off-by: Ian Jackson <ijackson@chiark.greenend.org.uk>
fork fails there. The failure message is confusing: so c.status()
returns an Err, the closure panics, and the test thinks the panic was
propagated from inside the child.
Signed-off-by: Ian Jackson <ijackson@chiark.greenend.org.uk>
Co-authored-by: Mara Bos <m-ou.se@m-ou.se>
This tests that we can indeed safely panic after fork, both
a raw libc::fork and in a Command pre_exec hook.
Signed-off-by: Ian Jackson <ijackson@chiark.greenend.org.uk>
Co-authored-by: Mara Bos <m-ou.se@m-ou.se>
This is safe (does not involve heap allocation) but we don't yet have
a test to ensure that stays true. That will come in a moment.
Signed-off-by: Ian Jackson <ijackson@chiark.greenend.org.uk>
Co-authored-by: Mara Bos <m-ou.se@m-ou.se>
Unwinding after fork() in the child is UB on some platforms, because
on those (including musl) malloc can be UB in the child of a
multithreaded program, and unwinding must box for the payload.
Even if it's safe, unwinding past fork() in the child causes whatever
traps the unwind to return twice. This is very strange and clearly
not desirable. With the default behaviour of the thread library, this
can even result in a panic in the child being transformed into zero
exit status (ie, success) as seen in the parent!
Fixes#79740.
Signed-off-by: Ian Jackson <ijackson@chiark.greenend.org.uk>
ExitStatus: print "exit status: {}" rather than "exit code: {}" on unix
Proper Unix terminology is "exit status" (vs "wait status"). "exit
code" is imprecise on Unix and therefore unclear. (As far as I can
tell, "exit code" is correct terminology on Windows.)
This new wording is unfortunately inconsistent with the identifier
names in the Rust stdlib.
It is the identifier names that are wrong, as discussed at length in eg
https://doc.rust-lang.org/nightly/std/process/struct.ExitStatus.htmlhttps://doc.rust-lang.org/nightly/std/os/unix/process/trait.ExitStatusExt.html
Unfortunately for API stability reasons it would be a lot of work, and
a lot of disruption, to change the names in the stdlib (eg to rename
`std::process::ExitStatus` to `std::process::ChildStatus` or
something), but we should fix the message output. Many (probably
most) readers of these messages about exit statuses will be users and
system administrators, not programmers, who won't even know that Rust
has this wrong terminology.
So I think the right thing is to fix the documentation (as I have
already done) and, now, the terminology in the implementation.
This is a user-visible change to the behaviour of all Rust programs
which run Unix subprocesses. Hopefully no-one is matching against the
exit status string, except perhaps in tests.
Proper Unix terminology is "exit status" (vs "wait status"). "exit
code" is imprecise on Unix and therefore unclear. (As far as I can
tell, "exit code" is correct terminology on Windows.)
This new wording is unfortunately inconsistent with the identifier
names in the Rust stdlib.
It is the identifier names that are wrong, as discussed at length in eg
https://doc.rust-lang.org/nightly/std/process/struct.ExitStatus.htmlhttps://doc.rust-lang.org/nightly/std/os/unix/process/trait.ExitStatusExt.html
Unfortunately for API stability reasons it would be a lot of work, and
a lot of disruption, to change the names in the stdlib (eg to rename
`std::process::ExitStatus` to `std::process::ChildStatus` or
something), but we should fix the message output. Many (probably
most) readers of these messages about exit statuses will be users and
system administrators, not programmers, who won't even know that Rust
has this wrong terminology.
So I think the right thing is to fix the documentation (as I have
already done) and, now, the terminology in the implementation.
This is a user-visible change to the behaviour of all Rust programs
which run Unix subprocesses. Hopefully no-one is matching against the
exit status string, except perhaps in tests.
Signed-off-by: Ian Jackson <ijackson@chiark.greenend.org.uk>
Add internal io::Error::new_const to avoid allocations.
This makes it possible to have a io::Error containing a message with zero allocations, and uses that everywhere to avoid the *three* allocations involved in `io::Error::new(kind, "message")`.
The function signature isn't perfect, because it needs a reference to the `&str`. So for now, this is just a `pub(crate)` function. Later, we'll be able to use `fn new_const<MSG: &'static str>(kind: ErrorKind)` to make that a bit better. (Then we'll also be able to use some ZST trickery if that would result in more efficient code.)
See https://github.com/rust-lang/rust/issues/83352
Do not attempt to unlock envlock in child process after a fork.
This implements the first two points from https://github.com/rust-lang/rust/issues/64718#issuecomment-793030479
This is a breaking change for cases where the environment is accessed in a Command::pre_exec closure. Except for single-threaded programs these uses were not correct anyway since they aren't async-signal safe.
Note that we had a ui test that explicitly tried `env::set_var` in `pre_exec`. As expected it failed with these changes when I tested locally.
Fixes to ExitStatus and its docs
* On Unix, properly display every possible wait status (and don't panic on weird values)
* In the documentation, be clear and consistent about "exit status" vs "wait status".
This is a breaking change for cases where the environment is
accessed in a Command::pre_exec closure. Except for
single-threaded programs these uses were not correct
anyway since they aren't async-signal safe.
If different unices have different bit patterns for WIFSTOPPED and
WIFCONTINUED then simply being glibc is probably not good enough for
this rather ad-hoc test to work. Do it on Linux only.
Signed-off-by: Ian Jackson <ijackson@chiark.greenend.org.uk>
Currently, on Nightly, this panics:
```
use std::process::ExitStatus;
use std::os::unix::process::ExitStatusExt;
fn main() {
let st = ExitStatus::from_raw(0x007f);
println!("st = {}", st);
}
```
This is because the impl of Display assumes that if .code() is None,
.signal() must be Some. That was a false assumption, although it was
true with buggy code before
5b1316f781
unix ExitStatus: Do not treat WIFSTOPPED as WIFSIGNALED
This is not likely to have affected many people in practice, because
`Command` will never produce such a wait status (`ExitStatus`).
Signed-off-by: Ian Jackson <ijackson@chiark.greenend.org.uk>
This is not particularly pretty but the current situation is a mess
and I don't think I'm making it significantly worse.
Signed-off-by: Ian Jackson <ijackson@chiark.greenend.org.uk>
A unix wait status can contain, at least, exit statuses, termination
signals, and stop signals.
WTERMSIG is only valid if WIFSIGNALED.
https://pubs.opengroup.org/onlinepubs/9699919799/functions/wait.html
It will not be easy to experience this bug with `Command`, because
that doesn't pass WUNTRACED. But you could make an ExitStatus
containing, say, a WIFSTOPPED, from a call to one of the libc wait
functions.
(In the WIFSTOPPED case, there is WSTOPSIG. But a stop signal is
encoded differently to a termination signal, so WTERMSIG and WSTOPSIG
are by no means the same.)
Signed-off-by: Ian Jackson <ijackson@chiark.greenend.org.uk>
If pthread mutex initialization fails, the failure will go unnoticed unless
debug assertions are enabled. Any subsequent use of mutex will also silently
fail, since return values from lock & unlock operations are similarly checked
only through debug assertions.
In some implementations the mutex initialization requires a memory
allocation and so it does fail in practice.
Check that initialization succeeds to ensure that mutex guarantees
mutual exclusion.
Use posix_spawn() on unix if program is a path
Previously `Command::spawn` would fall back to the non-posix_spawn based
implementation if the `PATH` environment variable was possibly changed.
On systems with a modern (g)libc `posix_spawn()` can be significantly
faster. If program is a path itself the `PATH` environment variable is
not used for the lookup and it should be safe to use the
`posix_spawnp()` method. [1]
We found this, because we have a cli application that effectively runs a
lot of subprocesses. It would sometimes noticeably hang while printing
output. Profiling showed that the process was spending the majority of
time in the kernel's `copy_page_range` function while spawning
subprocesses. During this time the process is completely blocked from
running, explaining why users were reporting the cli app hanging.
Through this we discovered that `std::process::Command` has a fast and
slow path for process execution. The fast path is backed by
`posix_spawnp()` and the slow path by fork/exec syscalls being called
explicitly. Using fork for process creation is supposed to be fast, but
it slows down as your process uses more memory. It's not because the
kernel copies the actual memory from the parent, but it does need to
copy the references to it (see `copy_page_range` above!). We ended up
using the slow path, because the command spawn implementation in falls
back to the slow path if it suspects the PATH environment variable was
changed.
Here is a smallish program demonstrating the slowdown before this code
change:
```
use std::process::Command;
use std::time::Instant;
fn main() {
let mut args = std::env::args().skip(1);
if let Some(size) = args.next() {
// Allocate some memory
let _xs: Vec<_> = std::iter::repeat(0)
.take(size.parse().expect("valid number"))
.collect();
let mut command = Command::new("/bin/sh");
command
.arg("-c")
.arg("echo hello");
if args.next().is_some() {
println!("Overriding PATH");
command.env("PATH", std::env::var("PATH").expect("PATH env var"));
}
let now = Instant::now();
let child = command
.spawn()
.expect("failed to execute process");
println!("Spawn took: {:?}", now.elapsed());
let output = child.wait_with_output().expect("failed to wait on process");
println!("Output: {:?}", output);
} else {
eprintln!("Usage: prog [size]");
std::process::exit(1);
}
()
}
```
Running it and passing different amounts of elements to use to allocate
memory shows that the time taken for `spawn()` can differ quite
significantly. In latter case the `posix_spawnp()` implementation is 30x
faster:
```
$ cargo run --release 10000000
...
Spawn took: 324.275µs
hello
$ cargo run --release 10000000 changepath
...
Overriding PATH
Spawn took: 2.346809ms
hello
$ cargo run --release 100000000
...
Spawn took: 387.842µs
hello
$ cargo run --release 100000000 changepath
...
Overriding PATH
Spawn took: 13.434677ms
hello
```
[1]: 5f72f9800b/posix/execvpe.c (L81)
