Clarify the behavior of rust.codegen-backends

Author: Kobzol

bootstrap.example.toml

@@ -740,11 +740,19 @@
 # result (broken, compiling, testing) into this JSON file.
 #rust.save-toolstates = <none> (path)
 
-# This is an array of the codegen backends that will be compiled for the rustc
-# that's being compiled. The default is to only build the LLVM codegen backend,
-# and currently the only standard options supported are `"llvm"`, `"cranelift"`
-# and `"gcc"`. The first backend in this list will be used as default by rustc
-# when no explicit backend is specified.
+# This array serves three distinct purposes:
+# - Backends in this list will be automatically compiled and included in the sysroot of each
+# rustc compiled by bootstrap.
+# - The first backend in this list will be configured as the **default codegen backend** by each
+# rustc compiled by bootstrap. In other words, if the first backend is e.g. cranelift, then when
+# we build a stage 1 rustc, it will by default compile Rust programs using the Cranelift backend.
+# This also means that stage 2 rustc would get built by the Cranelift backend.
+# - Running `x dist` (without additional arguments, or with `--include-default-paths`) will produce
+# a dist component/tarball for the Cranelift backend if it is included in this array.
+#
+# Note that the LLVM codegen backend is special and will always be built and distributed.
+#
+# Currently, the only standard options supported here are `"llvm"`, `"cranelift"` and `"gcc"`.
 #rust.codegen-backends = ["llvm"]
 
 # Indicates whether LLD will be compiled and made available in the sysroot for rustc to execute, and

src/bootstrap/src/core/build_steps/compile.rs

@@ -2190,7 +2190,7 @@ impl Step for Assemble {
             let _codegen_backend_span =
                 span!(tracing::Level::DEBUG, "building requested codegen backends").entered();
 
-            for backend in builder.config.codegen_backends(target_compiler.host) {
+            for backend in builder.config.enabled_codegen_backends(target_compiler.host) {
                 // FIXME: this is a horrible hack used to make `x check` work when other codegen
                 // backends are enabled.
                 // `x check` will check stage 1 rustc, which copies its rmetas to the stage0 sysroot.

src/bootstrap/src/core/build_steps/dist.rs

@@ -1406,7 +1406,7 @@ impl Step for CraneliftCodegenBackend {
         let clif_enabled_by_default = run
             .builder
             .config
-            .codegen_backends(run.builder.host_target)
+            .enabled_codegen_backends(run.builder.host_target)
             .contains(&CodegenBackendKind::Cranelift);
         run.alias("rustc_codegen_cranelift").default_condition(clif_enabled_by_default)
     }
@@ -1437,7 +1437,7 @@ impl Step for CraneliftCodegenBackend {
             return None;
         }
 
-        let mut tarball = Tarball::new(builder, &"rustc-codegen-cranelift", &target.triple);
+        let mut tarball = Tarball::new(builder, "rustc-codegen-cranelift", &target.triple);
         tarball.set_overlay(OverlayKind::RustcCodegenCranelift);
         tarball.is_preview(true);
         tarball.add_legal_and_readme_to("share/doc/rustc_codegen_cranelift");

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

@@ -3478,7 +3478,11 @@ impl Step for CodegenCranelift {
             return;
         }
 
-        if !builder.config.codegen_backends(run.target).contains(&CodegenBackendKind::Cranelift) {
+        if !builder
+            .config
+            .enabled_codegen_backends(run.target)
+            .contains(&CodegenBackendKind::Cranelift)
+        {
             builder.info("cranelift not in rust.codegen-backends. skipping");
             return;
         }
@@ -3605,7 +3609,7 @@ impl Step for CodegenGCC {
             return;
         }
 
-        if !builder.config.codegen_backends(run.target).contains(&CodegenBackendKind::Gcc) {
+        if !builder.config.enabled_codegen_backends(run.target).contains(&CodegenBackendKind::Gcc) {
             builder.info("gcc not in rust.codegen-backends. skipping");
             return;
         }

src/bootstrap/src/core/config/config.rs

@@ -1977,19 +1977,24 @@ impl Config {
             .unwrap_or(self.profiler)
     }
 
-    pub fn codegen_backends(&self, target: TargetSelection) -> &[CodegenBackendKind] {
+    /// Returns codegen backends that should be:
+    /// - Built and added to the sysroot when we build the compiler.
+    /// - Distributed when `x dist` is executed (if the codegen backend has a dist step).
+    pub fn enabled_codegen_backends(&self, target: TargetSelection) -> &[CodegenBackendKind] {
         self.target_config
             .get(&target)
             .and_then(|cfg| cfg.codegen_backends.as_deref())
             .unwrap_or(&self.rust_codegen_backends)
     }
 
-    pub fn jemalloc(&self, target: TargetSelection) -> bool {
-        self.target_config.get(&target).and_then(|cfg| cfg.jemalloc).unwrap_or(self.jemalloc)
+    /// Returns the codegen backend that should be configured as the *default* codegen backend
+    /// for a rustc compiled by bootstrap.
+    pub fn default_codegen_backend(&self, target: TargetSelection) -> Option<CodegenBackendKind> {
+        self.enabled_codegen_backends(target).first().cloned()
     }
 
-    pub fn default_codegen_backend(&self, target: TargetSelection) -> Option<CodegenBackendKind> {
-        self.codegen_backends(target).first().cloned()
+    pub fn jemalloc(&self, target: TargetSelection) -> bool {
+        self.target_config.get(&target).and_then(|cfg| cfg.jemalloc).unwrap_or(self.jemalloc)
     }
 
     pub fn rpath_enabled(&self, target: TargetSelection) -> bool {
@@ -2004,7 +2009,7 @@ impl Config {
     }
 
     pub fn llvm_enabled(&self, target: TargetSelection) -> bool {
-        self.codegen_backends(target).contains(&CodegenBackendKind::Llvm)
+        self.enabled_codegen_backends(target).contains(&CodegenBackendKind::Llvm)
     }
 
     pub fn llvm_libunwind(&self, target: TargetSelection) -> LlvmLibunwind {