summaryrefslogtreecommitdiffstats
path: root/vendor/cpufeatures/src
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-17 12:02:58 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-17 12:02:58 +0000
commit698f8c2f01ea549d77d7dc3338a12e04c11057b9 (patch)
tree173a775858bd501c378080a10dca74132f05bc50 /vendor/cpufeatures/src
parentInitial commit. (diff)
downloadrustc-698f8c2f01ea549d77d7dc3338a12e04c11057b9.tar.xz
rustc-698f8c2f01ea549d77d7dc3338a12e04c11057b9.zip
Adding upstream version 1.64.0+dfsg1.upstream/1.64.0+dfsg1
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'vendor/cpufeatures/src')
-rw-r--r--vendor/cpufeatures/src/aarch64.rs182
-rw-r--r--vendor/cpufeatures/src/lib.rs135
-rw-r--r--vendor/cpufeatures/src/x86.rs81
3 files changed, 398 insertions, 0 deletions
diff --git a/vendor/cpufeatures/src/aarch64.rs b/vendor/cpufeatures/src/aarch64.rs
new file mode 100644
index 000000000..6efdde1af
--- /dev/null
+++ b/vendor/cpufeatures/src/aarch64.rs
@@ -0,0 +1,182 @@
+//! ARM64 CPU feature detection support.
+//!
+//! Unfortunately ARM instructions to detect CPU features cannot be called from
+//! unprivileged userspace code, so this implementation relies on OS-specific
+//! APIs for feature detection.
+
+// Evaluate the given `$body` expression any of the supplied target features
+// are not enabled. Otherwise returns true.
+#[macro_export]
+#[doc(hidden)]
+macro_rules! __unless_target_features {
+ ($($tf:tt),+ => $body:expr ) => {
+ {
+ #[cfg(not(all($(target_feature=$tf,)*)))]
+ $body
+
+ #[cfg(all($(target_feature=$tf,)*))]
+ true
+ }
+ };
+}
+
+// Linux runtime detection of target CPU features using `getauxval`.
+#[cfg(any(target_os = "linux", target_os = "android"))]
+#[macro_export]
+#[doc(hidden)]
+macro_rules! __detect_target_features {
+ ($($tf:tt),+) => {{
+ let hwcaps = $crate::aarch64::getauxval_hwcap();
+ $($crate::check!(hwcaps, $tf) & )+ true
+ }};
+}
+
+/// Linux helper function for calling `getauxval` to get `AT_HWCAP`.
+#[cfg(any(target_os = "linux", target_os = "android"))]
+pub fn getauxval_hwcap() -> u64 {
+ unsafe { libc::getauxval(libc::AT_HWCAP) }
+}
+
+// MacOS runtime detection of target CPU features using `sysctlbyname`.
+#[cfg(target_os = "macos")]
+#[macro_export]
+#[doc(hidden)]
+macro_rules! __detect_target_features {
+ ($($tf:tt),+) => {{
+ $($crate::check!($tf) & )+ true
+ }};
+}
+
+// Linux `expand_check_macro`
+#[cfg(any(target_os = "linux", target_os = "android"))]
+macro_rules! __expand_check_macro {
+ ($(($name:tt, $hwcap:ident)),* $(,)?) => {
+ #[macro_export]
+ #[doc(hidden)]
+ macro_rules! check {
+ $(
+ ($hwcaps:expr, $name) => {
+ (($hwcaps & $crate::aarch64::hwcaps::$hwcap) != 0)
+ };
+ )*
+ }
+ };
+}
+
+// Linux `expand_check_macro`
+#[cfg(any(target_os = "linux", target_os = "android"))]
+__expand_check_macro! {
+ ("aes", AES), // Enable AES support.
+ ("sha2", SHA2), // Enable SHA1 and SHA256 support.
+ ("sha3", SHA3), // Enable SHA512 and SHA3 support.
+}
+
+/// Linux hardware capabilities mapped to target features.
+///
+/// Note that LLVM target features are coarser grained than what Linux supports
+/// and imply more capabilities under each feature. This module attempts to
+/// provide that mapping accordingly.
+///
+/// See this issue for more info: <https://github.com/RustCrypto/utils/issues/395>
+#[cfg(any(target_os = "linux", target_os = "android"))]
+pub mod hwcaps {
+ use libc::c_ulong;
+
+ pub const AES: c_ulong = libc::HWCAP_AES | libc::HWCAP_PMULL;
+ pub const SHA2: c_ulong = libc::HWCAP_SHA2;
+ pub const SHA3: c_ulong = libc::HWCAP_SHA3 | libc::HWCAP_SHA512;
+}
+
+// macOS `check!` macro.
+//
+// NOTE: several of these instructions (e.g. `aes`, `sha2`) can be assumed to
+// be present on all Apple ARM64 hardware.
+//
+// Newer CPU instructions now have nodes within sysctl's `hw.optional`
+// namespace, however the ones that do not can safely be assumed to be
+// present on all Apple ARM64 devices, now and for the foreseeable future.
+//
+// See discussion on this issue for more information:
+// <https://github.com/RustCrypto/utils/issues/378>
+#[cfg(target_os = "macos")]
+#[macro_export]
+#[doc(hidden)]
+macro_rules! check {
+ ("aes") => {
+ true
+ };
+ ("sha2") => {
+ true
+ };
+ ("sha3") => {
+ unsafe {
+ // `sha3` target feature implies SHA-512 as well
+ $crate::aarch64::sysctlbyname(b"hw.optional.armv8_2_sha512\0")
+ && $crate::aarch64::sysctlbyname(b"hw.optional.armv8_2_sha3\0")
+ }
+ };
+}
+
+/// macOS helper function for calling `sysctlbyname`.
+#[cfg(target_os = "macos")]
+pub unsafe fn sysctlbyname(name: &[u8]) -> bool {
+ assert_eq!(
+ name.last().cloned(),
+ Some(0),
+ "name is not NUL terminated: {:?}",
+ name
+ );
+
+ let mut value: u32 = 0;
+ let mut size = core::mem::size_of::<u32>();
+
+ let rc = libc::sysctlbyname(
+ name.as_ptr() as *const i8,
+ &mut value as *mut _ as *mut libc::c_void,
+ &mut size,
+ core::ptr::null_mut(),
+ 0,
+ );
+
+ assert_eq!(size, 4, "unexpected sysctlbyname(3) result size");
+ assert_eq!(rc, 0, "sysctlbyname returned error code: {}", rc);
+ value != 0
+}
+
+// iOS `check!` macro.
+//
+// Unfortunately iOS does not provide access to the `sysctl(3)` API which means
+// we can only return static values for CPU features which can be assumed to
+// be present on all Apple ARM64 hardware.
+//
+// See discussion on this issue for more information:
+// <https://github.com/RustCrypto/utils/issues/378>
+#[cfg(target_os = "ios")]
+#[macro_export]
+#[doc(hidden)]
+macro_rules! check {
+ ("aes") => {
+ true
+ };
+ ("sha2") => {
+ true
+ };
+ ("sha3") => {
+ false
+ };
+}
+
+// On other targets, runtime CPU feature detection is unavailable
+#[cfg(not(any(
+ target_os = "ios",
+ target_os = "linux",
+ target_os = "android",
+ target_os = "macos"
+)))]
+#[macro_export]
+#[doc(hidden)]
+macro_rules! __detect_target_features {
+ ($($tf:tt),+) => {
+ false
+ };
+}
diff --git a/vendor/cpufeatures/src/lib.rs b/vendor/cpufeatures/src/lib.rs
new file mode 100644
index 000000000..08b6e528d
--- /dev/null
+++ b/vendor/cpufeatures/src/lib.rs
@@ -0,0 +1,135 @@
+//! This crate provides macros for runtime CPU feature detection. It's intended
+//! as a stopgap until Rust [RFC 2725] adding first-class target feature detection
+//! macros to `libcore` is implemented.
+//!
+//! Supported target architectures:
+//! - `aarch64`: Linux and macOS/M4 only (ARM64 does not support OS-independent feature detection)
+//! - Target features: `aes`, `sha2`, `sha3`
+//! - `x86`/`x86_64`: OS independent and `no_std`-friendly
+//! - Target features: `adx`, `aes`, `avx`, `avx2`, `bmi1`, `bmi2`, `fma`,
+//! `mmx`, `pclmulqdq`, `popcnt`, `rdrand`, `rdseed`, `sgx`, `sha`, `sse`,
+//! `sse2`, `sse3`, `sse4.1`, `sse4.2`, `ssse3`
+//!
+//! If you would like detection support for a target feature which is not on
+//! this list, please [open a GitHub issue][gh].
+//!
+//! # Example
+//! ```
+//! # #[cfg(any(target_arch = "x86", target_arch = "x86_64"))]
+//! # {
+//! // This macro creates `cpuid_aes_sha` module
+//! cpufeatures::new!(cpuid_aes_sha, "aes", "sha");
+//!
+//! // `token` is a Zero Sized Type (ZST) value, which guarantees
+//! // that underlying static storage got properly initialized,
+//! // which allows to omit initialization branch
+//! let token: cpuid_aes_sha::InitToken = cpuid_aes_sha::init();
+//!
+//! if token.get() {
+//! println!("CPU supports both SHA and AES extensions");
+//! } else {
+//! println!("SHA and AES extensions are not supported");
+//! }
+//!
+//! // If stored value needed only once you can get stored value
+//! // omitting the token
+//! let val = cpuid_aes_sha::get();
+//! assert_eq!(val, token.get());
+//!
+//! // Additionally you can get both token and value
+//! let (token, val) = cpuid_aes_sha::init_get();
+//! assert_eq!(val, token.get());
+//! # }
+//! ```
+//!
+//! Note that if all tested target features are enabled via compiler options
+//! (e.g. by using `RUSTFLAGS`), the `get` method will always return `true`
+//! and `init` will not use CPUID instruction. Such behavior allows
+//! compiler to completely eliminate fallback code.
+//!
+//! After first call macro caches result and returns it in subsequent
+//! calls, thus runtime overhead for them is minimal.
+//!
+//! [RFC 2725]: https://github.com/rust-lang/rfcs/pull/2725
+//! [gh]: https://github.com/RustCrypto/utils/issues/new?title=cpufeatures:%20requesting%20support%20for%20CHANGEME%20target%20feature
+
+#![no_std]
+#![doc(
+ html_logo_url = "https://raw.githubusercontent.com/RustCrypto/media/6ee8e381/logo.svg",
+ html_favicon_url = "https://raw.githubusercontent.com/RustCrypto/media/6ee8e381/logo.svg"
+)]
+
+#[cfg(all(target_arch = "aarch64"))]
+#[doc(hidden)]
+pub mod aarch64;
+
+#[cfg(any(target_arch = "x86", target_arch = "x86_64"))]
+mod x86;
+
+#[cfg(not(any(target_arch = "aarch64", target_arch = "x86", target_arch = "x86_64")))]
+compile_error!("This crate works only on `aarch64`, `x86`, and `x86-64` targets.");
+
+/// Create module with CPU feature detection code.
+#[macro_export]
+macro_rules! new {
+ ($mod_name:ident, $($tf:tt),+ $(,)?) => {
+ mod $mod_name {
+ use core::sync::atomic::{AtomicU8, Ordering::Relaxed};
+
+ const UNINIT: u8 = u8::max_value();
+ static STORAGE: AtomicU8 = AtomicU8::new(UNINIT);
+
+ /// Initialization token
+ #[derive(Copy, Clone, Debug)]
+ pub struct InitToken(());
+
+ impl InitToken {
+ /// Get initialized value
+ #[inline(always)]
+ pub fn get(&self) -> bool {
+ $crate::__unless_target_features! {
+ $($tf),+ => {
+ STORAGE.load(Relaxed) == 1
+ }
+ }
+ }
+ }
+
+ /// Initialize underlying storage if needed and get
+ /// stored value and initialization token.
+ #[inline]
+ pub fn init_get() -> (InitToken, bool) {
+ let res = $crate::__unless_target_features! {
+ $($tf),+ => {
+ // Relaxed ordering is fine, as we only have a single atomic variable.
+ let val = STORAGE.load(Relaxed);
+
+ if val == UNINIT {
+ let res = $crate::__detect_target_features!($($tf),+);
+ STORAGE.store(res as u8, Relaxed);
+ res
+ } else {
+ val == 1
+ }
+ }
+ };
+
+ (InitToken(()), res)
+ }
+
+ /// Initialize underlying storage if needed and get
+ /// initialization token.
+ #[inline]
+ pub fn init() -> InitToken {
+ init_get().0
+ }
+
+ /// Initialize underlying storage if needed and get
+ /// stored value.
+ #[inline]
+ pub fn get() -> bool {
+ init_get().1
+ }
+ }
+ };
+}
diff --git a/vendor/cpufeatures/src/x86.rs b/vendor/cpufeatures/src/x86.rs
new file mode 100644
index 000000000..37e20ef6a
--- /dev/null
+++ b/vendor/cpufeatures/src/x86.rs
@@ -0,0 +1,81 @@
+//! x86/x86-64 CPU feature detection support.
+//!
+//! Portable, `no_std`-friendly implementation that relies on the x86 `CPUID`
+//! instruction for feature detection.
+
+// Evaluate the given `$body` expression any of the supplied target features
+// are not enabled. Otherwise returns true.
+//
+// The `$body` expression is not evaluated on SGX targets, and returns false
+// on these targets unless *all* supplied target features are enabled.
+#[macro_export]
+#[doc(hidden)]
+macro_rules! __unless_target_features {
+ ($($tf:tt),+ => $body:expr ) => {{
+ #[cfg(not(all($(target_feature=$tf,)*)))]
+ {
+ #[cfg(not(target_env = "sgx"))]
+ $body
+
+ // CPUID is not available on SGX targets
+ #[cfg(target_env = "sgx")]
+ false
+ }
+
+ #[cfg(all($(target_feature=$tf,)*))]
+ true
+ }};
+}
+
+// Use CPUID to detect the presence of all supplied target features.
+#[macro_export]
+#[doc(hidden)]
+macro_rules! __detect_target_features {
+ ($($tf:tt),+) => {{
+ #[cfg(target_arch = "x86")]
+ use core::arch::x86::{__cpuid, __cpuid_count};
+ #[cfg(target_arch = "x86_64")]
+ use core::arch::x86_64::{__cpuid, __cpuid_count};
+
+ let cr = unsafe {
+ [__cpuid(1), __cpuid_count(7, 0)]
+ };
+
+ $($crate::check!(cr, $tf) & )+ true
+ }};
+}
+
+macro_rules! __expand_check_macro {
+ ($(($name:tt, $i:expr, $reg:ident, $offset:expr)),* $(,)?) => {
+ #[macro_export]
+ #[doc(hidden)]
+ macro_rules! check {
+ $(
+ ($cr:expr, $name) => { ($cr[$i].$reg & (1 << $offset) != 0) };
+ )*
+ }
+ };
+}
+
+__expand_check_macro! {
+ ("mmx", 0, edx, 23),
+ ("sse", 0, edx, 25),
+ ("sse2", 0, edx, 26),
+ ("sse3", 0, ecx, 0),
+ ("pclmulqdq", 0, ecx, 1),
+ ("ssse3", 0, ecx, 9),
+ ("fma", 0, ecx, 12),
+ ("sse4.1", 0, ecx, 19),
+ ("sse4.2", 0, ecx, 20),
+ ("popcnt", 0, ecx, 23),
+ ("aes", 0, ecx, 25),
+ ("avx", 0, ecx, 28),
+ ("rdrand", 0, ecx, 30),
+ ("sgx", 1, ebx, 2),
+ ("bmi1", 1, ebx, 3),
+ ("avx2", 1, ebx, 5),
+ ("bmi2", 1, ebx, 8),
+ ("rdseed", 1, ebx, 18),
+ ("adx", 1, ebx, 19),
+ ("sha", 1, ebx, 29),
+}