Add initial version of snapshot tests to bootstrap

src/bootstrap/Cargo.lock

@@ -44,6 +44,7 @@ dependencies = [
  "fd-lock",
  "home",
  "ignore",
+ "insta",
  "junction",
  "libc",
  "object",
@@ -158,6 +159,18 @@ dependencies = [
  "cc",
 ]
 
+[[package]]
+name = "console"
+version = "0.15.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "054ccb5b10f9f2cbf51eb355ca1d05c2d279ce1804688d0db74b4733a5aeafd8"
+dependencies = [
+ "encode_unicode",
+ "libc",
+ "once_cell",
+ "windows-sys 0.59.0",
+]
+
 [[package]]
 name = "cpufeatures"
 version = "0.2.15"
@@ -218,6 +231,12 @@ dependencies = [
  "crypto-common",
 ]
 
+[[package]]
+name = "encode_unicode"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "34aa73646ffb006b8f5147f3dc182bd4bcb190227ce861fc4a4844bf8e3cb2c0"
+
 [[package]]
 name = "errno"
 version = "0.3.11"
@@ -323,6 +342,17 @@ dependencies = [
  "winapi-util",
 ]
 
+[[package]]
+name = "insta"
+version = "1.43.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "154934ea70c58054b556dd430b99a98c2a7ff5309ac9891597e339b5c28f4371"
+dependencies = [
+ "console",
+ "once_cell",
+ "similar",
+]
+
 [[package]]
 name = "itoa"
 version = "1.0.11"
@@ -675,6 +705,12 @@ version = "1.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
 
+[[package]]
+name = "similar"
+version = "2.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbbb5d9659141646ae647b42fe094daf6c6192d1620870b449d9557f748b2daa"
+
 [[package]]
 name = "smallvec"
 version = "1.13.2"

src/bootstrap/Cargo.toml

@@ -84,6 +84,7 @@ features = [
 [dev-dependencies]
 pretty_assertions = "1.4"
 tempfile = "3.15.0"
+insta = "1.43"
 
 # We care a lot about bootstrap's compile times, so don't include debuginfo for
 # dependencies, only bootstrap itself.

src/bootstrap/README.md

@@ -200,6 +200,10 @@ please file issues on the [Rust issue tracker][rust-issue-tracker].
 [rust-bootstrap-zulip]: https://rust-lang.zulipchat.com/#narrow/stream/t-infra.2Fbootstrap
 [rust-issue-tracker]: https://github.com/rust-lang/rust/issues
 
+## Testing
+
+To run bootstrap tests, execute `x test bootstrap`. If you want to bless snapshot tests, then install `cargo-insta` (`cargo install cargo-insta`) and then run `cargo insta review --manifest-path src/bootstrap/Cargo.toml`.
+
 ## Changelog
 
 Because we do not release bootstrap with versions, we also do not maintain CHANGELOG files. To

src/bootstrap/src/core/build_steps/test.rs

@@ -3059,6 +3059,8 @@ impl Step for Bootstrap {
         cargo
             .rustflag("-Cdebuginfo=2")
             .env("CARGO_TARGET_DIR", builder.out.join("bootstrap"))
+            // Needed for insta to correctly write pending snapshots to the right directories.
+            .env("INSTA_WORKSPACE_ROOT", &builder.src)
             .env("RUSTC_BOOTSTRAP", "1");
 
         // bootstrap tests are racy on directory creation so just run them one at a time.

src/bootstrap/src/core/builder/tests.rs

@@ -15,11 +15,12 @@ static TEST_TRIPLE_2: &str = "i686-unknown-hurd-gnu";
 static TEST_TRIPLE_3: &str = "i686-unknown-netbsd";
 
 fn configure(cmd: &str, host: &[&str], target: &[&str]) -> Config {
-    configure_with_args(&[cmd.to_owned()], host, target)
+    configure_with_args(&[cmd], host, target)
 }
 
-fn configure_with_args(cmd: &[String], host: &[&str], target: &[&str]) -> Config {
-    let mut config = Config::parse(Flags::parse(cmd));
+fn configure_with_args(cmd: &[&str], host: &[&str], target: &[&str]) -> Config {
+    let cmd = cmd.iter().copied().map(String::from).collect::<Vec<_>>();
+    let mut config = Config::parse(Flags::parse(&cmd));
     // don't save toolstates
     config.save_toolstates = None;
     config.set_dry_run(DryRun::SelfCheck);
@@ -67,7 +68,7 @@ fn run_build(paths: &[PathBuf], config: Config) -> Cache {
 fn check_cli<const N: usize>(paths: [&str; N]) {
     run_build(
         &paths.map(PathBuf::from),
-        configure_with_args(&paths.map(String::from), &[TEST_TRIPLE_1], &[TEST_TRIPLE_1]),
+        configure_with_args(&paths, &[TEST_TRIPLE_1], &[TEST_TRIPLE_1]),
     );
 }
 
@@ -1000,8 +1001,7 @@ mod sysroot_target_dirs {
 /// cg_gcc tests instead.
 #[test]
 fn test_test_compiler() {
-    let cmd = &["test", "compiler"].map(str::to_owned);
-    let config = configure_with_args(cmd, &[TEST_TRIPLE_1], &[TEST_TRIPLE_1]);
+    let config = configure_with_args(&["test", "compiler"], &[TEST_TRIPLE_1], &[TEST_TRIPLE_1]);
     let cache = run_build(&config.paths.clone(), config);
 
     let compiler = cache.contains::<test::CrateLibrustc>();
@@ -1034,8 +1034,7 @@ fn test_test_coverage() {
         // Print each test case so that if one fails, the most recently printed
         // case is the one that failed.
         println!("Testing case: {cmd:?}");
-        let cmd = cmd.iter().copied().map(str::to_owned).collect::<Vec<_>>();
-        let config = configure_with_args(&cmd, &[TEST_TRIPLE_1], &[TEST_TRIPLE_1]);
+        let config = configure_with_args(cmd, &[TEST_TRIPLE_1], &[TEST_TRIPLE_1]);
         let mut cache = run_build(&config.paths.clone(), config);
 
         let modes =
@@ -1207,8 +1206,7 @@ fn test_get_tool_rustc_compiler() {
 /// of `Any { .. }`.
 #[test]
 fn step_cycle_debug() {
-    let cmd = ["run", "cyclic-step"].map(str::to_owned);
-    let config = configure_with_args(&cmd, &[TEST_TRIPLE_1], &[TEST_TRIPLE_1]);
+    let config = configure_with_args(&["run", "cyclic-step"], &[TEST_TRIPLE_1], &[TEST_TRIPLE_1]);
 
     let err = panic::catch_unwind(|| run_build(&config.paths.clone(), config)).unwrap_err();
     let err = err.downcast_ref::<String>().unwrap().as_str();
@@ -1233,3 +1231,81 @@ fn any_debug() {
     // Downcasting to the underlying type should succeed.
     assert_eq!(x.downcast_ref::<MyStruct>(), Some(&MyStruct { x: 7 }));
 }
+
+/// The staging tests use insta for snapshot testing.
+/// See bootstrap's README on how to bless the snapshots.
+mod staging {
+    use crate::core::builder::tests::{
+        TEST_TRIPLE_1, configure, configure_with_args, render_steps, run_build,
+    };
+
+    #[test]
+    fn build_compiler_stage_1() {
+        let mut cache = run_build(
+            &["compiler".into()],
+            configure_with_args(&["build", "--stage", "1"], &[TEST_TRIPLE_1], &[TEST_TRIPLE_1]),
+        );
+        let steps = cache.into_executed_steps();
+        insta::assert_snapshot!(render_steps(&steps), @r"
+        [build] rustc 0 <target1> -> std 0 <target1>
+        [build] llvm <target1>
+        [build] rustc 0 <target1> -> rustc 1 <target1>
+        [build] rustc 0 <target1> -> rustc 1 <target1>
+        ");
+    }
+}
+
+/// Renders the executed bootstrap steps for usage in snapshot tests with insta.
+/// Only renders certain important steps.
+/// Each value in `steps` should be a tuple of (Step, step output).
+fn render_steps(steps: &[(Box<dyn Any>, Box<dyn Any>)]) -> String {
+    steps
+        .iter()
+        .filter_map(|(step, output)| {
+            // FIXME: implement an optional method on Step to produce metadata for test, instead
+            // of this downcasting
+            if let Some((rustc, output)) = downcast_step::<compile::Rustc>(step, output) {
+                Some(format!(
+                    "[build] {} -> {}",
+                    render_compiler(rustc.build_compiler),
+                    // FIXME: return the correct stage from the `Rustc` step, now it behaves weirdly
+                    render_compiler(Compiler::new(rustc.build_compiler.stage + 1, rustc.target)),
+                ))
+            } else if let Some((std, output)) = downcast_step::<compile::Std>(step, output) {
+                Some(format!(
+                    "[build] {} -> std {} <{}>",
+                    render_compiler(std.compiler),
+                    std.compiler.stage,
+                    std.target
+                ))
+            } else if let Some((llvm, output)) = downcast_step::<llvm::Llvm>(step, output) {
+                Some(format!("[build] llvm <{}>", llvm.target))
+            } else {
+                None
+            }
+        })
+        .map(|line| {
+            line.replace(TEST_TRIPLE_1, "target1")
+                .replace(TEST_TRIPLE_2, "target2")
+                .replace(TEST_TRIPLE_3, "target3")
+        })
+        .collect::<Vec<_>>()
+        .join("\n")
+}
+
+fn downcast_step<'a, S: Step>(
+    step: &'a Box<dyn Any>,
+    output: &'a Box<dyn Any>,
+) -> Option<(&'a S, &'a S::Output)> {
+    let Some(step) = step.downcast_ref::<S>() else {
+        return None;
+    };
+    let Some(output) = output.downcast_ref::<S::Output>() else {
+        return None;
+    };
+    Some((step, output))
+}
+
+fn render_compiler(compiler: Compiler) -> String {
+    format!("rustc {} <{}>", compiler.stage, compiler.host)
+}

src/bootstrap/src/utils/cache.rs

@@ -17,6 +17,7 @@ use std::borrow::Borrow;
 use std::cell::RefCell;
 use std::cmp::Ordering;
 use std::collections::HashMap;
+use std::fmt::Debug;
 use std::hash::{Hash, Hasher};
 use std::marker::PhantomData;
 use std::ops::Deref;
@@ -208,38 +209,51 @@ pub static INTERNER: LazyLock<Interner> = LazyLock::new(Interner::default);
 /// any type in its output. It is a write-once cache; values are never evicted,
 /// which means that references to the value can safely be returned from the
 /// `get()` method.
-#[derive(Debug)]
-pub struct Cache(
-    RefCell<
+#[derive(Debug, Default)]
+pub struct Cache {
+    cache: RefCell<
         HashMap<
             TypeId,
             Box<dyn Any>, // actually a HashMap<Step, Interned<Step::Output>>
         >,
     >,
-);
+    #[cfg(test)]
+    /// Contains steps in the same order in which they were executed
+    /// Useful for tests
+    /// Tuples (step, step output)
+    executed_steps: RefCell<Vec<(Box<dyn Any>, Box<dyn Any>)>>,
+}
 
 impl Cache {
     /// Creates a new empty cache.
     pub fn new() -> Cache {
-        Cache(RefCell::new(HashMap::new()))
+        Cache::default()
     }
 
     /// Stores the result of a computation step in the cache.
     pub fn put<S: Step>(&self, step: S, value: S::Output) {
-        let mut cache = self.0.borrow_mut();
+        let mut cache = self.cache.borrow_mut();
         let type_id = TypeId::of::<S>();
         let stepcache = cache
             .entry(type_id)
             .or_insert_with(|| Box::<HashMap<S, S::Output>>::default())
             .downcast_mut::<HashMap<S, S::Output>>()
             .expect("invalid type mapped");
         assert!(!stepcache.contains_key(&step), "processing {step:?} a second time");
+
+        #[cfg(test)]
+        {
+            let step: Box<dyn Any> = Box::new(step.clone());
+            let output: Box<dyn Any> = Box::new(value.clone());
+            self.executed_steps.borrow_mut().push((step, output));
+        }
+
         stepcache.insert(step, value);
     }
 
     /// Retrieves a cached result for the given step, if available.
     pub fn get<S: Step>(&self, step: &S) -> Option<S::Output> {
-        let mut cache = self.0.borrow_mut();
+        let mut cache = self.cache.borrow_mut();
         let type_id = TypeId::of::<S>();
         let stepcache = cache
             .entry(type_id)
@@ -252,8 +266,8 @@ impl Cache {
 
 #[cfg(test)]
 impl Cache {
-    pub fn all<S: Ord + Clone + Step>(&mut self) -> Vec<(S, S::Output)> {
-        let cache = self.0.get_mut();
+    pub fn all<S: Ord + Step>(&mut self) -> Vec<(S, S::Output)> {
+        let cache = self.cache.get_mut();
         let type_id = TypeId::of::<S>();
         let mut v = cache
             .remove(&type_id)
@@ -265,7 +279,12 @@ impl Cache {
     }
 
     pub fn contains<S: Step>(&self) -> bool {
-        self.0.borrow().contains_key(&TypeId::of::<S>())
+        self.cache.borrow().contains_key(&TypeId::of::<S>())
+    }
+
+    #[cfg(test)]
+    pub fn into_executed_steps(mut self) -> Vec<(Box<dyn Any>, Box<dyn Any>)> {
+        mem::take(&mut self.executed_steps.borrow_mut())
     }
 }