Auto merge of #120855 - bjorn3:split_metadata4, r=<try>

Introduce -Zsplit-metadata option

This will split the crate metadata out of library files. Instead only the svh and a bit of extra metadata is preserved to allow for loading the right rmeta file. This significantly reduces library size. In addition it allows for cheaper checks if different library files are the same crate.

A fair amount of the complexity in this PR is to work around the fact that cargo doesn't directly support this option yet.

Fixes #23366
Fixes #57076

Revives #93945

Author: bors

compiler/rustc_codegen_cranelift/build_system/tests.rs

@@ -475,6 +475,7 @@ impl<'a> TestRunner<'a> {
         cmd.arg("-Zunstable-options");
         cmd.arg("--check-cfg=cfg(no_unstable_features)");
         cmd.arg("--check-cfg=cfg(jit)");
+        cmd.arg("--emit=metadata,link");
         cmd.args(args);
         cmd
     }

compiler/rustc_codegen_ssa/src/back/link.rs

@@ -316,8 +316,11 @@ fn link_rlib<'a>(
 
     let trailing_metadata = match flavor {
         RlibFlavor::Normal => {
-            let (metadata, metadata_position) =
-                create_wrapper_file(sess, b".rmeta".to_vec(), codegen_results.metadata.raw_data());
+            let (metadata, metadata_position) = create_wrapper_file(
+                sess,
+                b".rmeta".to_vec(),
+                codegen_results.metadata.maybe_reference(),
+            );
             let metadata = emit_wrapper_file(sess, &metadata, tmpdir, METADATA_FILENAME);
             match metadata_position {
                 MetadataPosition::First => {

compiler/rustc_codegen_ssa/src/back/metadata.rs

@@ -528,8 +528,8 @@ pub fn create_compressed_metadata_file(
     symbol_name: &str,
 ) -> Vec<u8> {
     let mut packed_metadata = rustc_metadata::METADATA_HEADER.to_vec();
-    packed_metadata.write_all(&(metadata.raw_data().len() as u64).to_le_bytes()).unwrap();
-    packed_metadata.extend(metadata.raw_data());
+    packed_metadata.write_all(&(metadata.maybe_reference().len() as u64).to_le_bytes()).unwrap();
+    packed_metadata.extend(metadata.maybe_reference());
 
     let Some(mut file) = create_object_file(sess) else {
         return packed_metadata.to_vec();

compiler/rustc_driver_impl/src/lib.rs

@@ -677,6 +677,7 @@ fn list_metadata(early_dcx: &EarlyDiagCtxt, sess: &Session, metadata_loader: &dy
                 metadata_loader,
                 &mut v,
                 &sess.opts.unstable_opts.ls,
+                sess.cfg_version,
             )
             .unwrap();
             safe_println!("{}", String::from_utf8(v).unwrap());

compiler/rustc_interface/src/tests.rs

@@ -702,6 +702,7 @@ fn test_unstable_options_tracking_hash() {
     untracked!(shell_argfiles, true);
     untracked!(span_debug, true);
     untracked!(span_free_formats, true);
+    untracked!(split_metadata, true);
     untracked!(temps_dir, Some(String::from("abc")));
     untracked!(threads, 99);
     untracked!(time_llvm_passes, true);

compiler/rustc_metadata/src/fs.rs

@@ -50,7 +50,8 @@ pub fn encode_and_write_metadata(tcx: TyCtxt<'_>) -> (EncodedMetadata, bool) {
         .tempdir_in(out_filename.parent().unwrap_or_else(|| Path::new("")))
         .unwrap_or_else(|err| tcx.dcx().emit_fatal(FailedCreateTempdir { err }));
     let metadata_tmpdir = MaybeTempDir::new(metadata_tmpdir, tcx.sess.opts.cg.save_temps);
-    let metadata_filename = metadata_tmpdir.as_ref().join(METADATA_FILENAME);
+    let metadata_filename = metadata_tmpdir.as_ref().join("full.rmeta");
+    let metadata_reference_filename = metadata_tmpdir.as_ref().join("ref.rmeta");
 
     // Always create a file at `metadata_filename`, even if we have nothing to write to it.
     // This simplifies the creation of the output `out_filename` when requested.
@@ -60,9 +61,12 @@ pub fn encode_and_write_metadata(tcx: TyCtxt<'_>) -> (EncodedMetadata, bool) {
             std::fs::File::create(&metadata_filename).unwrap_or_else(|err| {
                 tcx.dcx().emit_fatal(FailedCreateFile { filename: &metadata_filename, err });
             });
+            std::fs::File::create(&metadata_reference_filename).unwrap_or_else(|err| {
+                tcx.dcx().emit_fatal(FailedCreateFile { filename: &metadata_filename, err });
+            });
         }
         MetadataKind::Uncompressed | MetadataKind::Compressed => {
-            encode_metadata(tcx, &metadata_filename);
+            encode_metadata(tcx, &metadata_filename, &metadata_reference_filename)
         }
     };
 
@@ -100,9 +104,10 @@ pub fn encode_and_write_metadata(tcx: TyCtxt<'_>) -> (EncodedMetadata, bool) {
 
     // Load metadata back to memory: codegen may need to include it in object files.
     let metadata =
-        EncodedMetadata::from_path(metadata_filename, metadata_tmpdir).unwrap_or_else(|err| {
-            tcx.dcx().emit_fatal(FailedCreateEncodedMetadata { err });
-        });
+        EncodedMetadata::from_path(metadata_filename, metadata_reference_filename, metadata_tmpdir)
+            .unwrap_or_else(|err| {
+                tcx.dcx().emit_fatal(FailedCreateEncodedMetadata { err });
+            });
 
     let need_metadata_module = metadata_kind == MetadataKind::Compressed;
 

compiler/rustc_metadata/src/locator.rs

@@ -243,7 +243,6 @@ use std::{cmp, fmt};
 pub(crate) struct CrateLocator<'a> {
     // Immutable per-session configuration.
     only_needs_metadata: bool,
-    sysroot: &'a Path,
     metadata_loader: &'a dyn MetadataLoader,
     cfg_version: &'static str,
 
@@ -319,7 +318,6 @@ impl<'a> CrateLocator<'a> {
 
         CrateLocator {
             only_needs_metadata,
-            sysroot: &sess.sysroot,
             metadata_loader,
             cfg_version: sess.cfg_version,
             crate_name,
@@ -569,31 +567,47 @@ impl<'a> CrateLocator<'a> {
                 debug!("skipping empty file");
                 continue;
             }
-            let (hash, metadata) =
-                match get_metadata_section(self.target, flavor, &lib, self.metadata_loader) {
-                    Ok(blob) => {
-                        if let Some(h) = self.crate_matches(&blob, &lib) {
-                            (h, blob)
-                        } else {
-                            info!("metadata mismatch");
-                            continue;
-                        }
-                    }
-                    Err(MetadataError::LoadFailure(err)) => {
-                        info!("no metadata found: {}", err);
-                        // The file was present and created by the same compiler version, but we
-                        // couldn't load it for some reason. Give a hard error instead of silently
-                        // ignoring it, but only if we would have given an error anyway.
-                        self.crate_rejections
-                            .via_invalid
-                            .push(CrateMismatch { path: lib, got: err });
-                        continue;
-                    }
-                    Err(err @ MetadataError::NotPresent(_)) => {
-                        info!("no metadata found: {}", err);
+            let (hash, metadata) = match get_metadata_section(
+                self.target,
+                flavor,
+                &lib,
+                self.metadata_loader,
+                self.cfg_version,
+            ) {
+                Ok(blob) => {
+                    if let Some(h) = self.crate_matches(&blob, &lib) {
+                        (h, blob)
+                    } else {
+                        info!("metadata mismatch");
                         continue;
                     }
-                };
+                }
+                Err(MetadataError::VersionMismatch { expected_version, found_version }) => {
+                    // The file was present and created by the same compiler version, but we
+                    // couldn't load it for some reason. Give a hard error instead of silently
+                    // ignoring it, but only if we would have given an error anyway.
+                    info!(
+                        "Rejecting via version: expected {} got {}",
+                        expected_version, found_version
+                    );
+                    self.crate_rejections
+                        .via_version
+                        .push(CrateMismatch { path: lib, got: found_version });
+                    continue;
+                }
+                Err(MetadataError::LoadFailure(err)) => {
+                    info!("no metadata found: {}", err);
+                    // The file was present and created by the same compiler version, but we
+                    // couldn't load it for some reason. Give a hard error instead of silently
+                    // ignoring it, but only if we would have given an error anyway.
+                    self.crate_rejections.via_invalid.push(CrateMismatch { path: lib, got: err });
+                    continue;
+                }
+                Err(err @ MetadataError::NotPresent(_)) => {
+                    info!("no metadata found: {}", err);
+                    continue;
+                }
+            };
             // If we see multiple hashes, emit an error about duplicate candidates.
             if slot.as_ref().is_some_and(|s| s.0 != hash) {
                 if let Some(candidates) = err_data {
@@ -610,33 +624,11 @@ impl<'a> CrateLocator<'a> {
                 continue;
             }
 
-            // Ok so at this point we've determined that `(lib, kind)` above is
-            // a candidate crate to load, and that `slot` is either none (this
-            // is the first crate of its kind) or if some the previous path has
-            // the exact same hash (e.g., it's the exact same crate).
-            //
-            // In principle these two candidate crates are exactly the same so
-            // we can choose either of them to link. As a stupidly gross hack,
-            // however, we favor crate in the sysroot.
-            //
-            // You can find more info in rust-lang/rust#39518 and various linked
-            // issues, but the general gist is that during testing libstd the
-            // compilers has two candidates to choose from: one in the sysroot
-            // and one in the deps folder. These two crates are the exact same
-            // crate but if the compiler chooses the one in the deps folder
-            // it'll cause spurious errors on Windows.
-            //
-            // As a result, we favor the sysroot crate here. Note that the
-            // candidates are all canonicalized, so we canonicalize the sysroot
-            // as well.
-            if let Some((prev, _)) = &ret {
-                let sysroot = self.sysroot;
-                let sysroot = try_canonicalize(sysroot).unwrap_or_else(|_| sysroot.to_path_buf());
-                if prev.starts_with(&sysroot) {
-                    continue;
-                }
+            if !metadata.get_header().is_reference {
+                // FIXME nicer error when only an rlib or dylib with is_reference is found
+                // and no .rmeta?
+                *slot = Some((hash, metadata, lib.clone()));
             }
-            *slot = Some((hash, metadata, lib.clone()));
             ret = Some((lib, kind));
         }
 
@@ -648,16 +640,6 @@ impl<'a> CrateLocator<'a> {
     }
 
     fn crate_matches(&mut self, metadata: &MetadataBlob, libpath: &Path) -> Option<Svh> {
-        let rustc_version = rustc_version(self.cfg_version);
-        let found_version = metadata.get_rustc_version();
-        if found_version != rustc_version {
-            info!("Rejecting via version: expected {} got {}", rustc_version, found_version);
-            self.crate_rejections
-                .via_version
-                .push(CrateMismatch { path: libpath.to_path_buf(), got: found_version });
-            return None;
-        }
-
         let header = metadata.get_header();
         if header.is_proc_macro_crate != self.is_proc_macro {
             info!(
@@ -736,10 +718,12 @@ impl<'a> CrateLocator<'a> {
                 let loc_canon = loc.canonicalized().clone();
                 let loc = loc.original();
                 if loc.file_name().unwrap().to_str().unwrap().ends_with(".rlib") {
+                    rmetas.insert(loc_canon.with_extension("rmeta"), PathKind::ExternFlag);
                     rlibs.insert(loc_canon, PathKind::ExternFlag);
                 } else if loc.file_name().unwrap().to_str().unwrap().ends_with(".rmeta") {
                     rmetas.insert(loc_canon, PathKind::ExternFlag);
                 } else {
+                    rmetas.insert(loc_canon.with_extension("rmeta"), PathKind::ExternFlag);
                     dylibs.insert(loc_canon, PathKind::ExternFlag);
                 }
             } else {
@@ -770,6 +754,7 @@ fn get_metadata_section<'p>(
     flavor: CrateFlavor,
     filename: &'p Path,
     loader: &dyn MetadataLoader,
+    cfg_version: &'static str,
 ) -> Result<MetadataBlob, MetadataError<'p>> {
     if !filename.exists() {
         return Err(MetadataError::NotPresent(filename));
@@ -847,13 +832,12 @@ fn get_metadata_section<'p>(
         }
     };
     let blob = MetadataBlob(raw_bytes);
-    if blob.is_compatible() {
-        Ok(blob)
-    } else {
-        Err(MetadataError::LoadFailure(format!(
-            "invalid metadata version found: {}",
-            filename.display()
-        )))
+    match blob.check_compatibility(cfg_version) {
+        Ok(()) => Ok(blob),
+        Err(version) => Err(MetadataError::VersionMismatch {
+            expected_version: cfg_version,
+            found_version: version,
+        }),
     }
 }
 
@@ -864,9 +848,10 @@ pub fn list_file_metadata(
     metadata_loader: &dyn MetadataLoader,
     out: &mut dyn Write,
     ls_kinds: &[String],
+    cfg_version: &'static str,
 ) -> IoResult<()> {
     let flavor = get_flavor_from_path(path);
-    match get_metadata_section(target, flavor, path, metadata_loader) {
+    match get_metadata_section(target, flavor, path, metadata_loader, cfg_version) {
         Ok(metadata) => metadata.list_crate_metadata(out, ls_kinds),
         Err(msg) => write!(out, "{msg}\n"),
     }
@@ -932,6 +917,8 @@ enum MetadataError<'a> {
     NotPresent(&'a Path),
     /// The file was present and invalid.
     LoadFailure(String),
+    /// The file was present, but compiled with a different rustc version.
+    VersionMismatch { expected_version: &'static str, found_version: String },
 }
 
 impl fmt::Display for MetadataError<'_> {
@@ -941,6 +928,12 @@ impl fmt::Display for MetadataError<'_> {
                 f.write_str(&format!("no such file: '{}'", filename.display()))
             }
             MetadataError::LoadFailure(msg) => f.write_str(msg),
+            MetadataError::VersionMismatch { expected_version, found_version } => {
+                f.write_str(&format!(
+                    "rustc version mismatch. expected {}, found {}",
+                    expected_version, found_version,
+                ))
+            }
         }
     }
 }

compiler/rustc_metadata/src/rmeta/decoder.rs

@@ -680,13 +680,23 @@ impl<'a, 'tcx, I: Idx, T> Decodable<DecodeContext<'a, 'tcx>> for LazyTable<I, T>
 implement_ty_decoder!(DecodeContext<'a, 'tcx>);
 
 impl MetadataBlob {
-    pub(crate) fn is_compatible(&self) -> bool {
-        self.blob().starts_with(METADATA_HEADER)
-    }
+    pub(crate) fn check_compatibility(&self, cfg_version: &'static str) -> Result<(), String> {
+        if !self.blob().starts_with(METADATA_HEADER) {
+            if self.blob().starts_with(b"rust") {
+                return Err("<unknown rustc version>".to_string());
+            }
+            return Err("<invalid metadata header>".to_string());
+        }
 
-    pub(crate) fn get_rustc_version(&self) -> String {
-        LazyValue::<String>::from_position(NonZeroUsize::new(METADATA_HEADER.len() + 8).unwrap())
-            .decode(self)
+        let found_version = LazyValue::<String>::from_position(
+            NonZeroUsize::new(METADATA_HEADER.len() + 8).unwrap(),
+        )
+        .decode(self);
+        if rustc_version(cfg_version) != found_version {
+            return Err(found_version);
+        }
+
+        Ok(())
     }
 
     fn root_pos(&self) -> NonZeroUsize {