[WIP] cpufeatures: aarch64 support (Linux and macOS/M4)

Adds preliminary support for runtime feature detection on `aarch64`
targets, presently restricted to the following set of target features
which are present on both `aarch64-unknown-linux-gnu` and
`aarch64-apple-darwin` targets:

- `aes`: AES support
- `sha2`: SHA1 and SHA256 support
- `sha3`: SHA512 and SHA3 support

Author: tarcieri

.github/workflows/cpufeatures.yml

@@ -17,18 +17,95 @@ env:
   RUSTFLAGS: "-Dwarnings"
 
 jobs:
-  test:
+  # Linux tests
+  linux:
+    strategy:
+      matrix:
+        include:
+          # 32-bit Linux/x86
+          - target: i686-unknown-linux-gnu
+            rust: 1.40.0 # MSRV
+            deps: sudo apt update && sudo apt install gcc-multilib
+          - target: i686-unknown-linux-gnu
+            rust: stable
+            deps: sudo apt update && sudo apt install gcc-multilib
+
+          # 64-bit Linux/x86_64
+          - target: x86_64-unknown-linux-gnu
+            rust: 1.40.0 # MSRV
+          - target: x86_64-unknown-linux-gnu
+            rust: stable
     runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: ${{ matrix.rust }}
+          target: ${{ matrix.target }}
+          override: true
+          profile: minimal
+      - run: ${{ matrix.deps }}
+      - run: cargo test --target ${{ matrix.target }} --release
+
+  # macOS tests
+  macos:
     strategy:
       matrix:
-        rust:
+        toolchain:
           - 1.40.0 # MSRV
           - stable
+    runs-on: macos-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: ${{ matrix.toolchain }}
+          target: x86_64-apple-darwin
+          override: true
+      - run: cargo test --release
+
+  # Windows tests
+  windows:
+    strategy:
+      matrix:
+        include:
+          # 64-bit Windows (GNU)
+          # TODO(tarcieri): try re-enabling this when we bump MSRV
+          #- target: x86_64-pc-windows-gnu
+          #  toolchain: 1.40.0 # MSRV
+          - target: x86_64-pc-windows-gnu
+            toolchain: stable
+    runs-on: windows-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: ${{ matrix.toolchain }}
+          target: ${{ matrix.target }}
+          override: true
+      - run: cargo test --target ${{ matrix.target }} --release
+
+  # Cross-compiled tests
+  cross:
+    strategy:
+      matrix:
+        include:
+          # ARM64
+          # TODO(tarcieri): try re-enabling this when we bump MSRV
+          #- target: aarch64-unknown-linux-gnu
+          #  rust: 1.40.0 # MSRV
+          - target: aarch64-unknown-linux-gnu
+            rust: stable
+    runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v1
-    - uses: actions-rs/toolchain@v1
-      with:
-        profile: minimal
-        toolchain: ${{ matrix.rust }}
-        override: true
-    - run: cargo test --release
+      - uses: actions/checkout@v2
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: ${{ matrix.rust }}
+          target: ${{ matrix.target }}
+          override: true
+          profile: minimal
+      - run: cargo install cross
+      - run: cross test --target ${{ matrix.target }} --release

Cargo.lock

@@ -1,12 +1,21 @@
 [package]
 name = "cpufeatures"
 version = "0.1.0" # Also update html_root_url in lib.rs when bumping this
+description = """
+Lightweight and efficient no-std compatible alternative to the
+is_x86_feature_detected! macro
+"""
 authors = ["RustCrypto Developers"]
 license = "MIT OR Apache-2.0"
-description = "Lightweight and efficient no-std compatible alternative to the is_x86_feature_detected macro"
 documentation = "https://docs.rs/cpufeatures"
 repository = "https://github.com/RustCrypto/utils"
 keywords = ["cpuid", "target-feature"]
 categories = ["no-std"]
 edition = "2018"
 readme = "README.md"
+
+[target.aarch64-apple-darwin.dependencies]
+libc = "0.2"
+
+[target.'cfg(all(target_arch = "aarch64", target_os = "linux"))'.dependencies]
+libc = "0.2"

cpufeatures/Cargo.toml

@@ -0,0 +1,138 @@
+/// 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.
+
+/// Create module with CPU feature detection code.
+#[macro_export]
+macro_rules! new {
+    ($mod_name:ident, $($tf:tt),+ $(,)? ) => {
+        mod $mod_name {
+            use core::sync::atomic::{AtomicU8, Ordering::Relaxed};
+
+            const UNINIT: u8 = u8::max_value();
+            static STORAGE: AtomicU8 = AtomicU8::new(UNINIT);
+
+            /// Initialization token
+            #[derive(Copy, Clone, Debug)]
+            pub struct InitToken(());
+
+            impl InitToken {
+                /// Get initialized value
+                #[inline(always)]
+                pub fn get(&self) -> bool {
+                    #[cfg(not(all($(target_feature=$tf, )*)))]
+                    let res = STORAGE.load(Relaxed) == 1;
+                    #[cfg(all($(target_feature=$tf, )*))]
+                    let res = true;
+                    res
+                }
+            }
+
+            /// Initialize underlying storage if needed and get
+            /// stored value and initialization token.
+            #[inline]
+            pub fn init_get() -> (InitToken, bool) {
+                #[cfg(not(all($(target_feature=$tf, )*)))]
+                let res = {
+                    // Relaxed ordering is fine, as we only have a single atomic variable.
+                    let val = STORAGE.load(Relaxed);
+                    if val == UNINIT {
+                        #[cfg(target_os = "linux")]
+                        let res = {
+                            let hwcaps = unsafe { libc::getauxval(libc::AT_HWCAP) };
+                            $(cpufeatures::check!(hwcaps, $tf) & )+ true
+                        }
+
+                        #[cfg(target_os = "macos")]
+                        let res = $(cpufeatures::check!($tf) & )+ true;
+
+                        STORAGE.store(res as u8, Relaxed);
+                        res
+                    } else {
+                        val == 1
+                    }
+                };
+                #[cfg(all($(target_feature=$tf, )*))]
+                let res = true;
+
+                (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
+            }
+        }
+    };
+}
+
+#[cfg(target_os = "linux")]
+macro_rules! expand_check_macro {
+    ($(($name:tt, $hwcap:expr)),* $(,)?) => {
+        #[macro_export]
+        #[doc(hidden)]
+        macro_rules! check {
+            $(
+                ($hwcaps:expr, $name) => { (($hwcaps & libc::$hwcap) != 0) };
+            )*
+        }
+    };
+}
+
+#[cfg(target_os = "linux")]
+expand_check_macro! {
+    ("aes",  HWCAP_AES),  // Enable AES support.
+    ("sha2", HWCAP_SHA2), // Enable SHA1 and SHA256 support.
+    ("sha3", HWCAP_SHA3), // Enable SHA512 and SHA3 support.
+}
+
+// TODO(tarcieri): extract this into a function?
+#[cfg(target_os = "macos")]
+#[macro_export]
+#[doc(hidden)]
+macro_rules! sysctlbyname {
+    // WARNING: `$name` MUST be a byte slice terminated by `\0`
+    ($name:expr) => {{
+        let mut value: u32 = 0;
+        let mut size = core::mem::size_of::<u32>();
+
+        let rc = unsafe {
+            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!(rc, 0, "sysctlbyname returned error code: {}", rc);
+        value != 0
+    }};
+}
+
+#[cfg(target_os = "macos")]
+#[macro_export]
+#[doc(hidden)]
+macro_rules! check {
+    ("aes") => {
+        true
+    };
+    ("sha2") => {
+        true
+    };
+    ("sha3") => {
+        cpufeatures::sysctlbyname!(b"hw.optional.armv8_2_sha3\0")
+    };
+}