Rollup merge of #125465 - weihanglo:opt-dist-vendor, r=Mark-Simulacrum

bootstrap: vendor crates required by opt-dist to collect profiles

These are the default package set required by opt-dist to correctly work,
hence for people wanting to build a production grade of rustc in a
sandboxed / air-gapped environment, these need to be vendored.

The size of `rustc-src-nightly.tar.xz` before and after this change:

* Before: 298M
* After: 323M (+8%)

Size change might or might not be a concern.
See the previous discussion: https://github.com/rust-lang/rust/pull/125166#issuecomment-2113626468

Previous efforts on making:

* https://github.com/rust-lang/rust/pull/125125
* https://github.com/rust-lang/rust/pull/125166

---

Note that extra works still need to be done to make it fully vendored.

* The current pinned rustc-perf uses `tempfile::Tempdir` as the working
  directory when collecting profiles from some of these packages.
  This "tmp" working directory usage make it impossible for Cargo to pick
  up the correct vendor sources setting in `.cargo/config.toml` bundled
  in the rustc-src tarball. [^1]
* opt-dist verifies the final built rustc against a subset of rustc test
  suite. However it rolls out its own `config.toml` without setting
  `vendor = true`, and that results in `./vendor/` directory removed.
  [^2]

[^1]: 4f313add60/collector/src/compile/benchmark/mod.rs (L164-L173)
[^2]: 606afbb617/src/tools/opt-dist/src/tests.rs (L62-L77)

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

@@ -1041,6 +1041,21 @@ impl Step for PlainSourceTarball {
                 .env("RUSTC_BOOTSTRAP", "1")
                 .current_dir(plain_dst_src);
 
+            // Vendor packages that are required by opt-dist to collect PGO profiles.
+            let pkgs_for_pgo_training = build_helper::LLVM_PGO_CRATES
+                .iter()
+                .chain(build_helper::RUSTC_PGO_CRATES)
+                .map(|pkg| {
+                    let mut manifest_path =
+                        builder.src.join("./src/tools/rustc-perf/collector/compile-benchmarks");
+                    manifest_path.push(pkg);
+                    manifest_path.push("Cargo.toml");
+                    manifest_path
+                });
+            for manifest_path in pkgs_for_pgo_training {
+                cmd.arg("--sync").arg(manifest_path);
+            }
+
             let config = if !builder.config.dry_run() {
                 t!(String::from_utf8(t!(cmd.output()).stdout))
             } else {

src/tools/build_helper/README.md

@@ -0,0 +1 @@
+Types and functions shared across tools in this workspace.

src/tools/build_helper/src/lib.rs

@@ -1,5 +1,30 @@
+//! Types and functions shared across tools in this workspace.
+
 pub mod ci;
 pub mod git;
 pub mod metrics;
 pub mod stage0_parser;
 pub mod util;
+
+/// The default set of crates for opt-dist to collect LLVM profiles.
+pub const LLVM_PGO_CRATES: &[&str] = &[
+    "syn-1.0.89",
+    "cargo-0.60.0",
+    "serde-1.0.136",
+    "ripgrep-13.0.0",
+    "regex-1.5.5",
+    "clap-3.1.6",
+    "hyper-0.14.18",
+];
+
+/// The default set of crates for opt-dist to collect rustc profiles.
+pub const RUSTC_PGO_CRATES: &[&str] = &[
+    "externs",
+    "ctfe-stress-5",
+    "cargo-0.60.0",
+    "token-stream-stress",
+    "match-stress",
+    "tuple-stress",
+    "diesel-1.4.8",
+    "bitmaps-3.1.0",
+];

src/tools/opt-dist/src/training.rs

@@ -3,30 +3,10 @@ use crate::exec::{cmd, CmdBuilder};
 use crate::utils::io::{count_files, delete_directory};
 use crate::utils::with_log_group;
 use anyhow::Context;
+use build_helper::{LLVM_PGO_CRATES, RUSTC_PGO_CRATES};
 use camino::{Utf8Path, Utf8PathBuf};
 use humansize::BINARY;
 
-const LLVM_PGO_CRATES: &[&str] = &[
-    "syn-1.0.89",
-    "cargo-0.60.0",
-    "serde-1.0.136",
-    "ripgrep-13.0.0",
-    "regex-1.5.5",
-    "clap-3.1.6",
-    "hyper-0.14.18",
-];
-
-const RUSTC_PGO_CRATES: &[&str] = &[
-    "externs",
-    "ctfe-stress-5",
-    "cargo-0.60.0",
-    "token-stream-stress",
-    "match-stress",
-    "tuple-stress",
-    "diesel-1.4.8",
-    "bitmaps-3.1.0",
-];
-
 fn init_compiler_benchmarks(
     env: &Environment,
     profiles: &[&str],

src/tools/tidy/src/deps.rs

@@ -67,6 +67,7 @@ pub(crate) const WORKSPACES: &[(&str, ExceptionList, Option<(&[&str], &[&str])>)
     //("src/tools/miri/test-cargo-miri", &[], None), // FIXME uncomment once all deps are vendored
     //("src/tools/miri/test_dependencies", &[], None), // FIXME uncomment once all deps are vendored
     ("src/tools/rust-analyzer", EXCEPTIONS_RUST_ANALYZER, None),
+    ("src/tools/rustc-perf", EXCEPTIONS_RUSTC_PERF, None),
     ("src/tools/x", &[], None),
     // tidy-alphabetical-end
 ];
@@ -142,6 +143,22 @@ const EXCEPTIONS_RUST_ANALYZER: ExceptionList = &[
     // tidy-alphabetical-end
 ];
 
+const EXCEPTIONS_RUSTC_PERF: ExceptionList = &[
+    // tidy-alphabetical-start
+    ("alloc-no-stdlib", "BSD-3-Clause"),
+    ("alloc-stdlib", "BSD-3-Clause"),
+    ("brotli", "BSD-3-Clause/MIT"),
+    ("brotli-decompressor", "BSD-3-Clause/MIT"),
+    ("encoding_rs", "(Apache-2.0 OR MIT) AND BSD-3-Clause"),
+    ("inferno", "CDDL-1.0"),
+    ("instant", "BSD-3-Clause"),
+    ("ring", NON_STANDARD_LICENSE), // see EXCEPTIONS_NON_STANDARD_LICENSE_DEPS for more.
+    ("ryu", "Apache-2.0 OR BSL-1.0"),
+    ("snap", "BSD-3-Clause"),
+    ("subtle", "BSD-3-Clause"),
+    // tidy-alphabetical-end
+];
+
 const EXCEPTIONS_CRANELIFT: ExceptionList = &[
     // tidy-alphabetical-start
     ("cranelift-bforest", "Apache-2.0 WITH LLVM-exception"),
@@ -178,6 +195,20 @@ const EXCEPTIONS_UEFI_QEMU_TEST: ExceptionList = &[
     ("r-efi", "MIT OR Apache-2.0 OR LGPL-2.1-or-later"), // LGPL is not acceptible, but we use it under MIT OR Apache-2.0
 ];
 
+/// Placeholder for non-standard license file.
+const NON_STANDARD_LICENSE: &str = "NON_STANDARD_LICENSE";
+
+/// These dependencies have non-standard licenses but are genenrally permitted.
+const EXCEPTIONS_NON_STANDARD_LICENSE_DEPS: &[&str] = &[
+    // `ring` is included because it is an optional dependency of `hyper`,
+    // which is a training data in rustc-perf for optimized build.
+    // The license of it is generally `ISC AND MIT AND OpenSSL`,
+    // though the `package.license` field is not set.
+    //
+    // See https://github.com/briansmith/ring/issues/902
+    "ring",
+];
+
 /// These are the root crates that are part of the runtime. The licenses for
 /// these and all their dependencies *must not* be in the exception list.
 const RUNTIME_CRATES: &[&str] = &["std", "core", "alloc", "test", "panic_abort", "panic_unwind"];
@@ -610,6 +641,11 @@ fn check_license_exceptions(metadata: &Metadata, exceptions: &[(&str, &str)], ba
         for pkg in metadata.packages.iter().filter(|p| p.name == *name) {
             match &pkg.license {
                 None => {
+                    if *license == NON_STANDARD_LICENSE
+                        && EXCEPTIONS_NON_STANDARD_LICENSE_DEPS.contains(&pkg.name.as_str())
+                    {
+                        continue;
+                    }
                     tidy_error!(
                         bad,
                         "dependency exception `{}` does not declare a license expression",

src/tools/tidy/src/extdeps.rs

@@ -4,7 +4,11 @@ use std::fs;
 use std::path::Path;
 
 /// List of allowed sources for packages.
-const ALLOWED_SOURCES: &[&str] = &["\"registry+https://github.com/rust-lang/crates.io-index\""];
+const ALLOWED_SOURCES: &[&str] = &[
+    r#""registry+https://github.com/rust-lang/crates.io-index""#,
+    // This is `rust_team_data` used by `site` in src/tools/rustc-perf,
+    r#""git+https://github.com/rust-lang/team#a5260e76d3aa894c64c56e6ddc8545b9a98043ec""#,
+];
 
 /// Checks for external package sources. `root` is the path to the directory that contains the
 /// workspace `Cargo.toml`.