Manage valgrind instrumentation with profiling cli

.gitignore

@@ -1,3 +1,5 @@
 /target
 .DS_Store
 .codspeed
+compile_commands.json
+.cache

crates/exec-harness/Cargo.toml

@@ -11,17 +11,19 @@ path = "src/main.rs"
 
 [dependencies]
 anyhow = { workspace = true }
-codspeed = "4.1.0"
+codspeed = "4.2.0"
 log = { workspace = true }
 env_logger = { workspace = true }
 clap = { workspace = true }
 serde_json = { workspace = true }
 serde = { workspace = true }
 humantime = "2.1"
 runner-shared = { path = "../runner-shared" }
-
-[dev-dependencies]
 tempfile = { workspace = true }
 
+[build-dependencies]
+cargo_metadata = "0.19"
+cc = "1"
+
 [package.metadata.dist]
 targets = ["aarch64-unknown-linux-musl", "x86_64-unknown-linux-musl"]

crates/exec-harness/build.rs

@@ -0,0 +1,194 @@
+//! Build script for exec-harness
+//!
+//! This script compiles the `libcodspeed_preload.so` shared library that is used
+//! to inject instrumentation into child processes via LD_PRELOAD.
+//!
+//! The library is built using the `core.c` and headers from the `codspeed` crate's
+//! `instrument-hooks` directory.
+//!
+//! # Environment Variables
+//!
+//! - `CODSPEED_INSTRUMENT_HOOKS_DIR`: Optional override for the instrument-hooks
+//!   source directory. If not set, the build script will locate it from the
+//!   `codspeed` crate in the cargo registry.
+
+use cargo_metadata::MetadataCommand;
+use std::env;
+use std::path::PathBuf;
+
+/// Shared constants for the preload library.
+/// These are passed as C defines during compilation and exported as environment
+/// variables for the Rust code to use via `env!()`.
+struct PreloadConstants {
+    /// Environment variable name for the benchmark URI.
+    uri_env: &'static str,
+    /// Integration name reported to CodSpeed.
+    integration_name: &'static str,
+    /// Integration version reported to CodSpeed.
+    /// This should match the version of the `codspeed` crate dependency.
+    integration_version: &'static str,
+}
+
+// TODO(COD-1736): Stop impersonating codspeed-rust 🥸
+const PRELOAD_CONSTANTS: PreloadConstants = PreloadConstants {
+    uri_env: "CODSPEED_BENCH_URI",
+    integration_name: "codspeed-rust",
+    integration_version: "4.2.0",
+};
+
+/// Filename for the preload shared library.
+const PRELOAD_LIB_FILENAME: &str = "libcodspeed_preload.so";
+
+/// Paths required to build the preload shared library.
+struct PreloadBuildPaths {
+    /// Path to the preload C source file (codspeed_preload.c).
+    preload_c: PathBuf,
+    /// Path to the core C source file from instrument-hooks.
+    core_c: PathBuf,
+    /// Path to the includes directory from instrument-hooks.
+    includes_dir: PathBuf,
+    /// Path where the output shared library will be written.
+    output_lib: PathBuf,
+}
+
+fn main() {
+    println!("cargo:rerun-if-changed=preload/codspeed_preload.c");
+    println!("cargo:rerun-if-env-changed=CODSPEED_INSTRUMENT_HOOKS_DIR");
+
+    // Export constants as environment variables for the Rust code
+    println!(
+        "cargo:rustc-env=CODSPEED_URI_ENV={}",
+        PRELOAD_CONSTANTS.uri_env
+    );
+    println!(
+        "cargo:rustc-env=CODSPEED_INTEGRATION_NAME={}",
+        PRELOAD_CONSTANTS.integration_name
+    );
+    println!(
+        "cargo:rustc-env=CODSPEED_INTEGRATION_VERSION={}",
+        PRELOAD_CONSTANTS.integration_version
+    );
+    println!("cargo:rustc-env=CODSPEED_PRELOAD_LIB_FILENAME={PRELOAD_LIB_FILENAME}");
+
+    let out_dir = PathBuf::from(env::var("OUT_DIR").unwrap());
+    let manifest_dir = PathBuf::from(env::var("CARGO_MANIFEST_DIR").unwrap());
+
+    // Try to get the instrument-hooks directory from the environment variable first,
+    // otherwise locate it from the codspeed crate
+    let instrument_hooks_dir = match env::var("CODSPEED_INSTRUMENT_HOOKS_DIR") {
+        Ok(dir) => PathBuf::from(dir),
+        Err(_) => find_codspeed_instrument_hooks_dir(),
+    };
+
+    // Build the preload shared library
+    let paths = PreloadBuildPaths {
+        preload_c: manifest_dir.join("preload/codspeed_preload.c"),
+        core_c: instrument_hooks_dir.join("dist/core.c"),
+        includes_dir: instrument_hooks_dir.join("includes"),
+        output_lib: out_dir.join(PRELOAD_LIB_FILENAME),
+    };
+    paths.check_sources_exist();
+    build_shared_library(&paths, &PRELOAD_CONSTANTS);
+}
+
+/// Build the shared library using the cc crate
+fn build_shared_library(paths: &PreloadBuildPaths, constants: &PreloadConstants) {
+    let uri_env_val = format!("\"{}\"", constants.uri_env);
+    let integration_name_val = format!("\"{}\"", constants.integration_name);
+    let integration_version_val = format!("\"{}\"", constants.integration_version);
+
+    let mut build = cc::Build::new();
+    build
+        .file(&paths.preload_c)
+        .file(&paths.core_c)
+        .include(&paths.includes_dir)
+        .pic(true)
+        .opt_level(2)
+        .cargo_metadata(false)
+        // Pass constants as C defines
+        .define("CODSPEED_URI_ENV", uri_env_val.as_str())
+        .define("CODSPEED_INTEGRATION_NAME", integration_name_val.as_str())
+        .define(
+            "CODSPEED_INTEGRATION_VERSION",
+            integration_version_val.as_str(),
+        )
+        // Suppress warnings from generated Zig code
+        .flag("-Wno-format")
+        .flag("-Wno-format-security")
+        .flag("-Wno-unused-but-set-variable")
+        .flag("-Wno-unused-const-variable")
+        .flag("-Wno-type-limits")
+        .flag("-Wno-uninitialized")
+        .flag("-Wno-overflow")
+        .flag("-Wno-unused-function");
+
+    // Compile source files to object files
+    let objects = build.compile_intermediates();
+
+    // Link object files into shared library
+    let compiler = build.get_compiler();
+    let mut link_cmd = compiler.to_command();
+    link_cmd
+        .arg("-shared")
+        .arg("-o")
+        .arg(&paths.output_lib)
+        .args(&objects)
+        .arg("-lpthread");
+
+    let status = link_cmd.status().expect("Failed to run linker");
+    if !status.success() {
+        panic!("Failed to link libcodspeed_preload.so");
+    }
+}
+
+/// Find the instrument-hooks directory from the codspeed crate using cargo_metadata
+fn find_codspeed_instrument_hooks_dir() -> PathBuf {
+    let metadata = MetadataCommand::new()
+        .exec()
+        .expect("Failed to run cargo metadata");
+
+    // Find the codspeed package in the resolved dependencies
+    let codspeed_pkg = metadata
+        .packages
+        .iter()
+        .find(|p| p.name == "codspeed")
+        .expect("codspeed crate not found in dependencies");
+
+    let codspeed_dir = codspeed_pkg
+        .manifest_path
+        .parent()
+        .expect("Failed to get codspeed crate directory");
+
+    let instrument_hooks_dir = codspeed_dir.join("instrument-hooks");
+
+    if !instrument_hooks_dir.exists() {
+        panic!("instrument-hooks directory not found at {instrument_hooks_dir}");
+    }
+
+    instrument_hooks_dir.into_std_path_buf()
+}
+
+impl PreloadBuildPaths {
+    /// Verify that all required source files and directories exist.
+    /// Panics with a descriptive message if any path is missing.
+    fn check_sources_exist(&self) {
+        if !self.core_c.exists() {
+            panic!(
+                "core.c not found at {}. Make sure the codspeed crate is available.",
+                self.core_c.display()
+            );
+        }
+        if !self.includes_dir.exists() {
+            panic!(
+                "includes directory not found at {}. Make sure the codspeed crate is available.",
+                self.includes_dir.display()
+            );
+        }
+        if !self.preload_c.exists() {
+            panic!(
+                "codspeed_preload.c not found at {}",
+                self.preload_c.display()
+            );
+        }
+    }
+}

crates/exec-harness/preload/codspeed_preload.c

@@ -0,0 +1,99 @@
+// LD_PRELOAD library for enabling Valgrind instrumentation in child processes
+//
+// This library is loaded via LD_PRELOAD into benchmark processes spawned by
+// exec-harness. It enables callgrind instrumentation on load and disables it on
+// exit, allowing exec-harness to measure arbitrary commands without requiring
+// them to link against instrument-hooks.
+//
+// Environment variables:
+//   CODSPEED_BENCH_URI - The benchmark URI to report (required)
+//   CODSPEED_PRELOAD_LOCK - Set by the first process to prevent child processes
+//                          from re-initializing instrumentation
+
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "core.h"
+
+#ifndef RUNNING_ON_VALGRIND
+// If somehow the core.h did not include the valgrind header, something is
+// wrong, but still have a fallback
+#warning "RUNNING_ON_VALGRIND not defined, headers may be missing"
+#define RUNNING_ON_VALGRIND 0
+#endif
+
+static const char *LOCK_ENV = "CODSPEED_PRELOAD_LOCK";
+
+// These constants are defined by the build script (build.rs) via -D flags
+#ifndef CODSPEED_URI_ENV
+#error "CODSPEED_URI_ENV must be defined by the build system"
+#endif
+#ifndef CODSPEED_INTEGRATION_NAME
+#error "CODSPEED_INTEGRATION_NAME must be defined by the build system"
+#endif
+#ifndef CODSPEED_INTEGRATION_VERSION
+#error "CODSPEED_INTEGRATION_VERSION must be defined by the build system"
+#endif
+
+static const char *URI_ENV = CODSPEED_URI_ENV;
+static const char *INTEGRATION_NAME = CODSPEED_INTEGRATION_NAME;
+static const char *INTEGRATION_VERSION = CODSPEED_INTEGRATION_VERSION;
+
+static InstrumentHooks *g_hooks = NULL;
+static const char *g_bench_uri = NULL;
+
+__attribute__((constructor)) static void codspeed_preload_init(void) {
+  // Skip initialization if not running under Valgrind yet.
+  // When using LD_PRELOAD with Valgrind, the constructor runs twice:
+  // once before Valgrind takes over, and once after. We only want to
+  // initialize when Valgrind is active.
+  //
+  // This is purely empirical, and is not (yet) backed up by documented
+  // behavior.
+  if (!RUNNING_ON_VALGRIND) {
+    return;
+  }
+
+  // Check if another process already owns the instrumentation
+  if (getenv(LOCK_ENV)) {
+    return;
+  }
+
+  // Set the lock to prevent child processes from initializing
+  setenv(LOCK_ENV, "1", 1);
+
+  g_bench_uri = getenv(URI_ENV);
+  if (!g_bench_uri) {
+    return;
+  }
+
+  g_hooks = instrument_hooks_init();
+  if (!g_hooks) {
+    return;
+  }
+
+  instrument_hooks_set_integration(g_hooks, INTEGRATION_NAME,
+                                   INTEGRATION_VERSION);
+
+  if (instrument_hooks_start_benchmark_inline(g_hooks) != 0) {
+    instrument_hooks_deinit(g_hooks);
+    g_hooks = NULL;
+    return;
+  }
+}
+
+__attribute__((destructor)) static void codspeed_preload_fini(void) {
+  // If the process is not the owner of the lock, this means g_hooks was not
+  // initialized
+  if (!g_hooks) {
+    return;
+  }
+
+  instrument_hooks_stop_benchmark_inline(g_hooks);
+
+  int32_t pid = getpid();
+  instrument_hooks_set_executed_benchmark(g_hooks, pid, g_bench_uri);
+
+  instrument_hooks_deinit(g_hooks);
+  g_hooks = NULL;
+}