Auto merge of #83640 - bjorn3:shared_metadata_reader, r=nagisa

Use the object crate for metadata reading

This allows sharing the metadata reader between cg_llvm, cg_clif and other codegen backends.

This is not currently useful for rlib reading with cg_spirv ([rust-gpu](https://github.com/EmbarkStudios/rust-gpu/)) as it uses tar rather than ar as .rlib format, but it is useful for dylib reading required for loading proc macros. (cc `@eddyb)`

The object crate is already trusted as dependency of libstd through backtrace. As far as I know it supports reading all object file formats used by targets for which we support rust dylibs with crate metadata, but I am not certain. If this happens to not be the case, I could keep using LLVM for reading dylib metadata.

Marked as WIP for a perf run and as it is based on #83637.

3 files changed, 77 insertions, 0 deletions

diff --git a/compiler/rustc_codegen_ssa/Cargo.toml b/compiler/rustc_codegen_ssa/Cargo.toml
index c6764662fa5..68f40d5f863 100644
--- a/compiler/rustc_codegen_ssa/Cargo.toml
+++ b/compiler/rustc_codegen_ssa/Cargo.toml
@@ -33,3 +33,8 @@ rustc_index = { path = "../rustc_index" }
 rustc_macros = { path = "../rustc_macros" }
 rustc_target = { path = "../rustc_target" }
 rustc_session = { path = "../rustc_session" }
+
+[dependencies.object]
+version = "0.22.0"
+default-features = false
+features = ["read_core", "elf", "macho", "pe", "unaligned", "archive"]
diff --git a/compiler/rustc_codegen_ssa/src/back/metadata.rs b/compiler/rustc_codegen_ssa/src/back/metadata.rs
new file mode 100644
index 00000000000..37d1f8ecc83
--- /dev/null
+++ b/compiler/rustc_codegen_ssa/src/back/metadata.rs
@@ -0,0 +1,71 @@
+//! Reading of the rustc metadata for rlibs and dylibs
+
+use std::fs::File;
+use std::path::Path;
+
+use rustc_data_structures::memmap::Mmap;
+use rustc_data_structures::owning_ref::OwningRef;
+use rustc_data_structures::rustc_erase_owner;
+use rustc_data_structures::sync::MetadataRef;
+use rustc_middle::middle::cstore::MetadataLoader;
+use rustc_target::spec::Target;
+
+use crate::METADATA_FILENAME;
+
+/// The default metadata loader. This is used by cg_llvm and cg_clif.
+///
+/// # Metadata location
+///
+/// <dl>
+/// <dt>rlib</dt>
+/// <dd>The metadata can be found in the `lib.rmeta` file inside of the ar archive.</dd>
+/// <dt>dylib</dt>
+/// <dd>The metadata can be found in the `.rustc` section of the shared library.</dd>
+/// </dl>
+pub struct DefaultMetadataLoader;
+
+fn load_metadata_with(
+    path: &Path,
+    f: impl for<'a> FnOnce(&'a [u8]) -> Result<&'a [u8], String>,
+) -> Result<MetadataRef, String> {
+    let file =
+        File::open(path).map_err(|e| format!("failed to open file '{}': {}", path.display(), e))?;
+    let data = unsafe { Mmap::map(file) }
+        .map_err(|e| format!("failed to mmap file '{}': {}", path.display(), e))?;
+    let metadata = OwningRef::new(data).try_map(f)?;
+    return Ok(rustc_erase_owner!(metadata.map_owner_box()));
+}
+
+impl MetadataLoader for DefaultMetadataLoader {
+    fn get_rlib_metadata(&self, _target: &Target, path: &Path) -> Result<MetadataRef, String> {
+        load_metadata_with(path, |data| {
+            let archive = object::read::archive::ArchiveFile::parse(&*data)
+                .map_err(|e| format!("failed to parse rlib '{}': {}", path.display(), e))?;
+
+            for entry_result in archive.members() {
+                let entry = entry_result
+                    .map_err(|e| format!("failed to parse rlib '{}': {}", path.display(), e))?;
+                if entry.name() == METADATA_FILENAME.as_bytes() {
+                    return Ok(entry.data());
+                }
+            }
+
+            Err(format!("metadata not found in rlib '{}'", path.display()))
+        })
+    }
+
+    fn get_dylib_metadata(&self, _target: &Target, path: &Path) -> Result<MetadataRef, String> {
+        use object::{Object, ObjectSection};
+
+        load_metadata_with(path, |data| {
+            let file = object::File::parse(&data)
+                .map_err(|e| format!("failed to parse dylib '{}': {}", path.display(), e))?;
+            file.section_by_name(".rustc")
+                .ok_or_else(|| format!("no .rustc section in '{}'", path.display()))?
+                .data()
+                .map_err(|e| {
+                    format!("failed to read .rustc section in '{}': {}", path.display(), e)
+                })
+        })
+    }
+}
diff --git a/compiler/rustc_codegen_ssa/src/back/mod.rs b/compiler/rustc_codegen_ssa/src/back/mod.rs
index 20ca503d43f..d11ed54eb20 100644
--- a/compiler/rustc_codegen_ssa/src/back/mod.rs
+++ b/compiler/rustc_codegen_ssa/src/back/mod.rs
@@ -3,6 +3,7 @@ pub mod command;
 pub mod link;
 pub mod linker;
 pub mod lto;
+pub mod metadata;
 pub mod rpath;
 pub mod symbol_export;
 pub mod write;