asm: introduce a new x64 assembler

cranelift/assembler-x64/Cargo.toml

@@ -0,0 +1,23 @@
+[package]
+name = "cranelift-assembler-x64"
+description = "A Cranelift-specific x64 assembler"
+version = "0.117.0"
+license = "Apache-2.0 WITH LLVM-exception"
+edition.workspace = true
+
+[dependencies]
+arbitrary = { version = "1.3.2", features = ["derive"] }
+capstone = "0.12.0"
+
+[dev-dependencies]
+arbtest = "0.3.1"
+
+[build-dependencies]
+cranelift-assembler-x64-meta = { path = "meta" }
+
+[lints.clippy]
+all = "deny"
+pedantic = "warn"
+module_name_repetitions = { level = "allow", priority = 1 }
+similar_names = { level = "allow", priority = 1 }
+wildcard_imports = { level = "allow", priority = 1 }

cranelift/assembler-x64/README.md

@@ -0,0 +1,36 @@
+# `cranelift-assembler-x64`
+
+A Cranelift-specific x64 assembler. Unlike the existing `cranelift-codegen`
+assembler, this assembler uses instructions, not instruction classes, as the
+core abstraction.
+
+### Use
+
+Like `cranelift-codegen`, using this assembler starts with `enum Inst`. For
+convenience, a `main.rs` script prints the path to this generated code:
+
+```console
+$ cat $(cargo run)
+#[derive(arbitrary::Arbitrary, Debug)]
+pub enum Inst {
+    andb_i(andb_i),
+    andw_i(andw_i),
+    andl_i(andl_i),
+    ...
+```
+
+### Test
+
+In order to check that this assembler emits correct machine code, we fuzz it
+against a known-good disassembler. We can run a quick, one-second check:
+
+```console
+$ cargo test -- --nocapture
+```
+
+Or we can run the fuzzer indefinitely:
+
+```console
+$ cargo +nightly fuzz run -s none roundtrip -j16
+```
+

cranelift/assembler-x64/build.rs

@@ -0,0 +1,24 @@
+use cranelift_assembler_x64_meta as meta;
+use std::env;
+use std::path::Path;
+
+fn main() {
+    println!("cargo:rerun-if-changed=build.rs");
+
+    let out_dir = env::var("OUT_DIR").expect("The OUT_DIR environment variable must be set");
+    let out_dir = Path::new(&out_dir);
+    let built_files = [
+        meta::generate_rust_assembler(out_dir.join("assembler.rs")),
+        meta::generate_isle_macro(out_dir.join("assembler-isle-macro.rs")),
+        meta::generate_isle_definitions(out_dir.join("assembler-definitions.isle")),
+    ];
+
+    println!(
+        "cargo:rustc-env=ASSEMBLER_BUILT_FILES={}",
+        built_files
+            .iter()
+            .map(|p| p.to_string_lossy().to_string())
+            .collect::<Vec<_>>()
+            .join(":")
+    );
+}

cranelift/assembler-x64/fuzz/.gitignore

@@ -0,0 +1,4 @@
+target
+corpus
+artifacts
+coverage

cranelift/assembler-x64/fuzz/Cargo.toml

@@ -0,0 +1,21 @@
+[package]
+name = "cranelift-assembler-x64-fuzz"
+version = "0.0.0"
+publish = false
+edition = "2021"
+
+[package.metadata]
+cargo-fuzz = true
+
+[dependencies]
+libfuzzer-sys = "0.4"
+cranelift-assembler-x64 = { path = ".." }
+
+[[bin]]
+name = "roundtrip"
+path = "fuzz_targets/roundtrip.rs"
+test = false
+doc = false
+bench = false
+
+[workspace]

cranelift/assembler-x64/fuzz/fuzz_targets/roundtrip.rs

@@ -0,0 +1,8 @@
+#![no_main]
+
+use cranelift_assembler_x64::{fuzz, Inst};
+use libfuzzer_sys::fuzz_target;
+
+fuzz_target!(|inst: Inst<fuzz::FuzzRegs>| {
+    fuzz::roundtrip(&inst);
+});

cranelift/assembler-x64/meta/.rustfmt.toml

@@ -0,0 +1,5 @@
+# This extra configuration allows defining extra-long lines in
+# `src/instructions`.
+fn_call_width = 100
+max_width = 110
+struct_lit_width = 50

cranelift/assembler-x64/meta/Cargo.toml

@@ -0,0 +1,15 @@
+[package]
+name = "cranelift-assembler-x64-meta"
+description = "Generate a Cranelift-specific assembler for x64 instructions"
+version = "0.117.0"
+license = "Apache-2.0 WITH LLVM-exception"
+edition.workspace = true
+
+[dependencies]
+
+[lints.clippy]
+all = "deny"
+pedantic = "warn"
+enum_glob_use = { level = "allow", priority = 1 }
+just_underscores_and_digits = { level = "allow", priority = 1 }
+wildcard_imports = { level = "allow", priority = 1 }