Add libgccjit dist generation

5 files changed, 248 insertions, 7 deletions

diff --git a/src/bootstrap/src/core/build_steps/dist.rs b/src/bootstrap/src/core/build_steps/dist.rs
index 4957de2e1b7..2928f169b1a 100644
--- a/src/bootstrap/src/core/build_steps/dist.rs
+++ b/src/bootstrap/src/core/build_steps/dist.rs
@@ -2273,6 +2273,7 @@ impl Step for RustDev {
         tarball.permit_symlinks(true);
 
         builder.ensure(crate::core::build_steps::llvm::Llvm { target });
+        builder.ensure(crate::core::build_steps::gcc::Gcc { target });
 
         let src_bindir = builder.llvm_out(target).join("bin");
         // If updating this, you likely want to change
@@ -2308,6 +2309,15 @@ impl Step for RustDev {
         // just broadly useful to be able to link against the bundled LLVM.
         tarball.add_dir(builder.llvm_out(target).join("include"), "include");
 
+        let libgccjit_path = builder.gcc_out(target).join("install/lib/libgccjit.so");
+        if libgccjit_path.exists() {
+            tarball.add_dir(libgccjit_path, "libgccjit.so");
+            tarball.add_dir(
+                builder.gcc_out(target).join("install/lib/libgccjit.so.0"),
+                "libgccjit.so.0",
+            );
+        }
+
         // Copy libLLVM.so to the target lib dir as well, so the RPATH like
         // `$ORIGIN/../lib` can find it. It may also be used as a dependency
         // of `rustc-dev` to support the inherited `-lLLVM` when using the
diff --git a/src/bootstrap/src/core/build_steps/gcc.rs b/src/bootstrap/src/core/build_steps/gcc.rs
new file mode 100644
index 00000000000..c11782c5b14
--- /dev/null
+++ b/src/bootstrap/src/core/build_steps/gcc.rs
@@ -0,0 +1,226 @@
+//! Compilation of native dependencies like LLVM.
+//!
+//! Native projects like LLVM unfortunately aren't suited just yet for
+//! compilation in build scripts that Cargo has. This is because the
+//! compilation takes a *very* long time but also because we don't want to
+//! compile LLVM 3 times as part of a normal bootstrap (we want it cached).
+//!
+//! LLVM and compiler-rt are essentially just wired up to everything else to
+//! ensure that they're always in place if needed.
+
+use std::fs;
+use std::path::{Path, PathBuf};
+use std::sync::OnceLock;
+
+use crate::core::builder::{Builder, RunConfig, ShouldRun, Step};
+use crate::core::config::TargetSelection;
+use crate::utils::exec::command;
+use crate::utils::helpers::{self, t};
+use crate::{generate_smart_stamp_hash, Kind};
+
+use super::llvm::HashStamp;
+
+pub struct Meta {
+    stamp: HashStamp,
+    out_dir: PathBuf,
+    install_dir: PathBuf,
+    root: PathBuf,
+}
+
+pub enum GccBuildStatus {
+    AlreadyBuilt,
+    ShouldBuild(Meta),
+}
+
+/// This returns whether we've already previously built GCC.
+///
+/// It's used to avoid busting caches during x.py check -- if we've already built
+/// GCC, it's fine for us to not try to avoid doing so.
+pub fn prebuilt_gcc_config(builder: &Builder<'_>, target: TargetSelection) -> GccBuildStatus {
+    // If we have gcc submodule initialized already, sync it.
+    builder.update_existing_submodule(&Path::new("src").join("gcc"));
+
+    // FIXME (GuillaumeGomez): To be done once gccjit has been built in the CI.
+    // builder.config.maybe_download_ci_gcc();
+
+    // Initialize the llvm submodule if not initialized already.
+    builder.update_submodule(&Path::new("src").join("gcc"));
+
+    let root = "src/gcc";
+    let out_dir = builder.gcc_out(target).join("build");
+    let install_dir = builder.gcc_out(target).join("install");
+
+    static STAMP_HASH_MEMO: OnceLock<String> = OnceLock::new();
+    let smart_stamp_hash = STAMP_HASH_MEMO.get_or_init(|| {
+        generate_smart_stamp_hash(
+            &builder.config.src.join("src/llvm-project"),
+            builder.in_tree_llvm_info.sha().unwrap_or_default(),
+        )
+    });
+
+    let stamp = out_dir.join("gcc-finished-building");
+    let stamp = HashStamp::new(stamp, Some(smart_stamp_hash));
+
+    if stamp.is_done() {
+        if stamp.hash.is_none() {
+            builder.info(
+                "Could not determine the GCC submodule commit hash. \
+                     Assuming that an GCC rebuild is not necessary.",
+            );
+            builder.info(&format!(
+                "To force GCC to rebuild, remove the file `{}`",
+                stamp.path.display()
+            ));
+        }
+        return GccBuildStatus::AlreadyBuilt;
+    }
+
+    GccBuildStatus::ShouldBuild(Meta { stamp, out_dir, install_dir, root: root.into() })
+}
+
+// FIXME (GuillaumeGomez): When gcc-ci-download option is added, uncomment this code.
+// /// This retrieves the GCC sha we *want* to use, according to git history.
+// pub(crate) fn detect_gcc_sha(config: &Config, is_git: bool) -> String {
+//     let gcc_sha = if is_git {
+//         // We proceed in 2 steps. First we get the closest commit that is actually upstream. Then we
+//         // walk back further to the last bors merge commit that actually changed GCC. The first
+//         // step will fail on CI because only the `auto` branch exists; we just fall back to `HEAD`
+//         // in that case.
+//         let closest_upstream = get_git_merge_base(&config.git_config(), Some(&config.src))
+//             .unwrap_or_else(|_| "HEAD".into());
+//         let mut rev_list = config.git();
+//         rev_list.args(&[
+//             PathBuf::from("rev-list"),
+//             format!("--author={}", config.stage0_metadata.config.git_merge_commit_email).into(),
+//             "-n1".into(),
+//             "--first-parent".into(),
+//             closest_upstream.into(),
+//             "--".into(),
+//             config.src.join("src/gcc"),
+//             config.src.join("src/bootstrap/download-ci-gcc-stamp"),
+//             // the GCC shared object file is named `gcc-12-rust-{version}-nightly`
+//             config.src.join("src/version"),
+//         ]);
+//         output(&mut rev_list).trim().to_owned()
+//     } else if let Some(info) = channel::read_commit_info_file(&config.src) {
+//         info.sha.trim().to_owned()
+//     } else {
+//         "".to_owned()
+//     };
+
+//     if gcc_sha.is_empty() {
+//         eprintln!("error: could not find commit hash for downloading LLVM");
+//         eprintln!("HELP: maybe your repository history is too shallow?");
+//         eprintln!("HELP: consider disabling `download-ci-gcc`");
+//         eprintln!("HELP: or fetch enough history to include one upstream commit");
+//         panic!();
+//     }
+
+//     gcc_sha
+// }
+
+// /// Returns whether the CI-found GCC is currently usable.
+// ///
+// /// This checks both the build triple platform to confirm we're usable at all,
+// /// and then verifies if the current HEAD matches the detected GCC SHA head,
+// /// in which case GCC is indicated as not available.
+// pub(crate) fn is_ci_gcc_available(config: &Config, asserts: bool) -> bool {
+//     // This is currently all tier 1 targets and tier 2 targets with host tools
+//     // (since others may not have CI artifacts)
+//     // https://doc.rust-lang.org/rustc/platform-support.html#tier-1
+//     let supported_platforms = [
+//         // tier 1
+//         ("x86_64-unknown-linux-gnu", true),
+//     ];
+
+//     if !supported_platforms.contains(&(&*config.build.triple, asserts))
+//         && (asserts || !supported_platforms.contains(&(&*config.build.triple, true)))
+//     {
+//         return false;
+//     }
+
+//     if is_ci_gcc_modified(config) {
+//         eprintln!("Detected GCC as non-available: running in CI and modified GCC in this change");
+//         return false;
+//     }
+
+//     true
+// }
+
+// /// Returns true if we're running in CI with modified GCC (and thus can't download it)
+// pub(crate) fn is_ci_gcc_modified(config: &Config) -> bool {
+//     CiEnv::is_ci() && config.rust_info.is_managed_git_subrepository() && {
+//         // We assume we have access to git, so it's okay to unconditionally pass
+//         // `true` here.
+//         let gcc_sha = detect_gcc_sha(config, true);
+//         let head_sha = output(config.git().arg("rev-parse").arg("HEAD"));
+//         let head_sha = head_sha.trim();
+//         gcc_sha == head_sha
+//     }
+// }
+
+#[derive(Debug, Clone, Hash, PartialEq, Eq)]
+pub struct Gcc {
+    pub target: TargetSelection,
+}
+
+impl Step for Gcc {
+    type Output = bool;
+
+    const ONLY_HOSTS: bool = true;
+
+    fn should_run(run: ShouldRun<'_>) -> ShouldRun<'_> {
+        run.path("src/gcc")
+    }
+
+    fn make_run(run: RunConfig<'_>) {
+        run.builder.ensure(Gcc { target: run.target });
+    }
+
+    /// Compile GCC for `target`.
+    fn run(self, builder: &Builder<'_>) -> bool {
+        let target = self.target;
+        if !target.contains("linux") || !target.contains("x86_64") {
+            return false;
+        }
+
+        // If GCC has already been built or been downloaded through download-ci-gcc, we avoid
+        // building it again.
+        let Meta { stamp, out_dir, install_dir, root } = match prebuilt_gcc_config(builder, target)
+        {
+            GccBuildStatus::AlreadyBuilt => return true,
+            GccBuildStatus::ShouldBuild(m) => m,
+        };
+
+        let _guard = builder.msg_unstaged(Kind::Build, "GCC", target);
+        t!(stamp.remove());
+        let _time = helpers::timeit(builder);
+        t!(fs::create_dir_all(&out_dir));
+
+        if builder.config.dry_run() {
+            return true;
+        }
+
+        builder.run(
+            command(root.join("configure"))
+                .current_dir(&out_dir)
+                .arg("--enable-host-shared")
+                .arg("--enable-languages=jit")
+                .arg("--enable-checking=release")
+                .arg("--disable-bootstrap")
+                .arg("--disable-multilib")
+                .arg(format!("--prefix={}", install_dir.display())),
+        );
+        builder.run(command("make").current_dir(&out_dir).arg(format!("-j{}", builder.jobs())));
+        builder.run(command("make").current_dir(&out_dir).arg("install"));
+
+        t!(builder.symlink_file(
+            install_dir.join("lib/libgccjit.so"),
+            install_dir.join("lib/libgccjit.so.0")
+        ));
+
+        t!(stamp.write());
+
+        true
+    }
+}
diff --git a/src/bootstrap/src/core/build_steps/llvm.rs b/src/bootstrap/src/core/build_steps/llvm.rs
index 442638d3203..d729952adce 100644
--- a/src/bootstrap/src/core/build_steps/llvm.rs
+++ b/src/bootstrap/src/core/build_steps/llvm.rs
@@ -1242,17 +1242,17 @@ fn supported_sanitizers(
     }
 }
 
-struct HashStamp {
-    path: PathBuf,
-    hash: Option<Vec<u8>>,
+pub(super) struct HashStamp {
+    pub(super) path: PathBuf,
+    pub(super) hash: Option<Vec<u8>>,
 }
 
 impl HashStamp {
-    fn new(path: PathBuf, hash: Option<&str>) -> Self {
+    pub(super) fn new(path: PathBuf, hash: Option<&str>) -> Self {
         HashStamp { path, hash: hash.map(|s| s.as_bytes().to_owned()) }
     }
 
-    fn is_done(&self) -> bool {
+    pub(super) fn is_done(&self) -> bool {
         match fs::read(&self.path) {
             Ok(h) => self.hash.as_deref().unwrap_or(b"") == h.as_slice(),
             Err(e) if e.kind() == io::ErrorKind::NotFound => false,
@@ -1262,7 +1262,7 @@ impl HashStamp {
         }
     }
 
-    fn remove(&self) -> io::Result<()> {
+    pub(super) fn remove(&self) -> io::Result<()> {
         match fs::remove_file(&self.path) {
             Ok(()) => Ok(()),
             Err(e) => {
@@ -1275,7 +1275,7 @@ impl HashStamp {
         }
     }
 
-    fn write(&self) -> io::Result<()> {
+    pub(super) fn write(&self) -> io::Result<()> {
         fs::write(&self.path, self.hash.as_deref().unwrap_or(b""))
     }
 }
diff --git a/src/bootstrap/src/core/build_steps/mod.rs b/src/bootstrap/src/core/build_steps/mod.rs
index 004174e35e1..fcb6abea434 100644
--- a/src/bootstrap/src/core/build_steps/mod.rs
+++ b/src/bootstrap/src/core/build_steps/mod.rs
@@ -5,6 +5,7 @@ pub(crate) mod compile;
 pub(crate) mod dist;
 pub(crate) mod doc;
 pub(crate) mod format;
+pub(crate) mod gcc;
 pub(crate) mod install;
 pub(crate) mod llvm;
 pub(crate) mod perf;
diff --git a/src/bootstrap/src/lib.rs b/src/bootstrap/src/lib.rs
index c76ce340956..4ae78511669 100644
--- a/src/bootstrap/src/lib.rs
+++ b/src/bootstrap/src/lib.rs
@@ -765,6 +765,10 @@ impl Build {
         self.out.join(&*target.triple).join("enzyme")
     }
 
+    fn gcc_out(&self, target: TargetSelection) -> PathBuf {
+        self.out.join(&*target.triple).join("gcc")
+    }
+
     fn lld_out(&self, target: TargetSelection) -> PathBuf {
         self.out.join(target).join("lld")
     }