Tighten the bounds on atomic Ordering in std::sys::unix::weak::Weak
This moves reading this from multiple SeqCst reads to Relaxed read + Acquire fence if we are actually going to use the data.
Would love to avoid the Acquire fence, but doing so would need Ordering::Consume, which neither Rust, nor LLVM supports (a shame, since this fence is hardly free on ARM, which is what I was hoping to improve).
r? ``@Amanieu`` (Sorry for always picking you, but I know a lot of people wouldn't feel comfortable reviewing atomic ordering changes)
linux: try to use libc getrandom to allow interposition
We'll try to use a weak `getrandom` symbol first, because that allows
things like `LD_PRELOAD` interposition. For example, perf measurements
might want to disable randomness to get reproducible results. If the
weak symbol is not found, we fall back to a raw `SYS_getrandom` call.
Rollup of 9 pull requests
Successful merges:
- #77939 (Ensure that the source code display is working with DOS backline)
- #78138 (Upgrade dlmalloc to version 0.2)
- #78967 (Make codegen tests compatible with extra inlining)
- #79027 (Limit storage duration of inlined always live locals)
- #79077 (document that __rust_alloc is also magic to our LLVM fork)
- #79088 (clarify `span_label` documentation)
- #79097 (Code block invalid html tag lint)
- #79105 (std: Fix test `symlink_hard_link` on Windows)
- #79107 (build-manifest: strip newline from rustc version)
Failed merges:
r? `@ghost`
`@rustbot` modify labels: rollup
Upgrade dlmalloc to version 0.2
In preparation of adding dynamic memory management support for SGXv2-enabled platforms, the dlmalloc crate has been refactored. More specifically, support has been added to implement platform specification outside of the dlmalloc crate. (see https://github.com/alexcrichton/dlmalloc-rs/pull/15)
This PR upgrades dlmalloc to version 0.2 for the `wasm` and `sgx` targets.
As the dlmalloc changes have received a positive review, but have not been merged yet, this PR contains a commit to prevent tidy from aborting CI prematurely.
cc: `@jethrogb`
Make the libstd build script smaller
Of all sysroot crates currently only compiler_builtins, miniz_oxide and std require a build script. compiler_builtins uses to conditionally enable certain features and possibly compile a C version ([source](63ccaf11f0/build.rs)), miniz_oxide only uses it to detect if liballoc is supported as the MSRV is 1.34.0 instead of the 1.36.0 which stabilized liballoc ([source](28514ec09f/miniz_oxide/build.rs)). std now only uses it to enable `freebsd12` when the `RUST_STD_FREEBSD_12_ABI` env var is set, to determine if `restricted-std` should be set, to set the `STD_ENV_ARCH` env var identical to `CARGO_CFG_TARGET_ARCH`, and to unconditionally enable `backtrace_in_libstd`.
If all build scripts were to be removed, it would be possible for rustc to completely compile it's own sysroot. It currently requires a rustc version that already has an available libstd to compile the build scripts. If rustc can completely compile it's own sysroot, rustbuild could be simplified to not forcefully use the bootstrap compiler for build scripts.
`@rustbot` modify labels: +T-compiler +libs-impl
We'll try to use a weak `getrandom` symbol first, because that allows
things like `LD_PRELOAD` interposition. For example, perf measurements
might want to disable randomness to get reproducible results. If the
weak symbol is not found, we fall back to a raw `SYS_getrandom` call.
Fix an intrinsic invocation on threaded wasm
This looks like it was forgotten to get updated in #74482 and wasm with
threads isn't built on CI so we didn't catch this by accident.
specialize io::copy to use copy_file_range, splice or sendfile
Fixes#74426.
Also covers #60689 but only as an optimization instead of an official API.
The specialization only covers std-owned structs so it should avoid the problems with #71091
Currently linux-only but it should be generalizable to other unix systems that have sendfile/sosplice and similar.
There is a bit of optimization potential around the syscall count. Right now it may end up doing more syscalls than the naive copy loop when doing short (<8KiB) copies between file descriptors.
The test case executes the following:
```
[pid 103776] statx(3, "", AT_STATX_SYNC_AS_STAT|AT_EMPTY_PATH, STATX_ALL, {stx_mask=STATX_ALL|STATX_MNT_ID, stx_attributes=0, stx_mode=S_IFREG|0644, stx_size=17, ...}) = 0
[pid 103776] write(4, "wxyz", 4) = 4
[pid 103776] write(4, "iklmn", 5) = 5
[pid 103776] copy_file_range(3, NULL, 4, NULL, 5, 0) = 5
```
0-1 `stat` calls to identify the source file type. 0 if the type can be inferred from the struct from which the FD was extracted
𝖬 `write` to drain the `BufReader`/`BufWriter` wrappers. only happen when buffers are present. 𝖬 ≾ number of wrappers present. If there is a write buffer it may absorb the read buffer contents first so only result in a single write. Vectored writes would also be an option but that would require more invasive changes to `BufWriter`.
𝖭 `copy_file_range`/`splice`/`sendfile` until file size, EOF or the byte limit from `Take` is reached. This should generally be *much* more efficient than the read-write loop and also have other benefits such as DMA offload or extent sharing.
## Benchmarks
```
OLD
test io::tests::bench_file_to_file_copy ... bench: 21,002 ns/iter (+/- 750) = 6240 MB/s [ext4]
test io::tests::bench_file_to_file_copy ... bench: 35,704 ns/iter (+/- 1,108) = 3671 MB/s [btrfs]
test io::tests::bench_file_to_socket_copy ... bench: 57,002 ns/iter (+/- 4,205) = 2299 MB/s
test io::tests::bench_socket_pipe_socket_copy ... bench: 142,640 ns/iter (+/- 77,851) = 918 MB/s
NEW
test io::tests::bench_file_to_file_copy ... bench: 14,745 ns/iter (+/- 519) = 8889 MB/s [ext4]
test io::tests::bench_file_to_file_copy ... bench: 6,128 ns/iter (+/- 227) = 21389 MB/s [btrfs]
test io::tests::bench_file_to_socket_copy ... bench: 13,767 ns/iter (+/- 3,767) = 9520 MB/s
test io::tests::bench_socket_pipe_socket_copy ... bench: 26,471 ns/iter (+/- 6,412) = 4951 MB/s
```
Previously EOVERFLOW handling was only applied for io::copy specialization
but not for fs::copy sharing the same code.
Additionally we lower the chunk size to 1GB since we have a user report
that older kernels may return EINVAL when passing 0x8000_0000
but smaller values succeed.
Android builds use feature level 14, the libc wrapper for splice is gated
on feature level 21+ so we have to invoke the syscall directly.
Additionally the emulator doesn't seem to support it so we also have to
add ENOSYS checks.
Update thread and futex APIs to work with Emscripten
This updates the thread and futex APIs in `std` to match the APIs exposed by
Emscripten. This allows threads to run on `wasm32-unknown-emscripten` and the
thread parker to compile without errors related to the missing `futex` module.
To make use of this, Rust code must be compiled with `-C target-feature=atomics`
and Emscripten must link with `-pthread`.
I have confirmed this works well locally when building multithreaded crates.
Attempting to enable `std` thread tests currently fails for seemingly obscure
reasons and Emscripten is currently disabled in CI, so further work is needed to
have proper test coverage here.
This updates the thread and futex APIs in `std` to match the APIs exposed by
Emscripten. This allows threads to run on `wasm32-unknown-emscripten` and the
thread parker to compile without errors related to the missing `futex` module.
To make use of this, Rust code must be compiled with `-C target-feature=atomics`
and Emscripten must link with `-pthread`.
I have confirmed this works well locally when building multithreaded crates.
Attempting to enable `std` thread tests currently fails for seemingly obscure
reasons and Emscripten is currently disabled in CI, so further work is needed to
have proper test coverage here.
Define `fs::hard_link` to not follow symlinks.
POSIX leaves it [implementation-defined] whether `link` follows symlinks.
In practice, for example, on Linux it does not and on FreeBSD it does.
So, switch to `linkat`, so that we can pick a behavior rather than
depending on OS defaults.
Pick the option to not follow symlinks. This is somewhat arbitrary, but
seems the less surprising choice because hard linking is a very
low-level feature which requires the source and destination to be on
the same mounted filesystem, and following a symbolic link could end
up in a different mounted filesystem.
[implementation-defined]: https://pubs.opengroup.org/onlinepubs/9699919799/functions/link.html
`#![deny(unsafe_op_in_unsafe_fn)]` in sys/hermit
Partial fix of #73904.
This encloses ``unsafe`` operations in ``unsafe fn`` in ``sys/hermit``.
Some unsafe blocks are not well documented because some system-based functions lack documents.
`#[deny(unsafe_op_in_unsafe_fn)]` in sys/wasm
This is part of #73904.
This encloses unsafe operations in unsafe fn in `libstd/sys/wasm`.
@rustbot modify labels: F-unsafe-block-in-unsafe-fn
revise Hermit's mutex interface to support the behaviour of StaticMutex
rust-lang/rust#77147 simplifies things by splitting this Mutex type into two types matching the two use cases: StaticMutex and MovableMutex. To support the new behavior of StaticMutex, we move part of the mutex implementation into libstd.
The interface to the OS changed. Consequently, I removed a few functions, which aren't longer needed.
According to [the bionic status page], `linkat` has only been available
since API level 21. Since Android is based on Linux and Linux's `link`
doesn't follow symlinks, just use `link` on Android.
[the bionic status page]: https://android.googlesource.com/platform/bionic/+/master/docs/status.md
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)
