Make #[used] work when linking with ld64

Author: madsmtm

compiler/rustc_codegen_ssa/src/back/apple.rs

@@ -26,6 +26,82 @@ pub(super) fn macho_platform(target: &Target) -> u32 {
     }
 }
 
+/// Add relocation and section data needed for a symbol to be considered
+/// undefined by ld64.
+///
+/// Inherently very architecture-specific (unfortunately).
+///
+/// # New architectures
+///
+/// The values here can be found by compiling the following program:
+///
+/// ```c
+/// void foo(void);
+///
+/// void use_foo() {
+///     foo();
+/// }
+/// ```
+///
+/// With:
+///
+/// ```console
+/// $ clang -c foo.c -O2 -g0 -fno-exceptions -target $CLANG_TARGET
+/// ```
+///
+/// And then inspecting with `objdump -d foo.o` and/or:
+///
+/// ```no_run
+/// use object::read::macho::{MachHeader, MachOFile};
+/// use object::{File, Object, ObjectSection};
+///
+/// fn read(file: MachOFile<'_, impl MachHeader>) {
+///     for section in file.sections() {
+///         dbg!(section.name().unwrap(), section.data().unwrap(), section.align());
+///         for reloc in section.relocations() {
+///             dbg!(reloc);
+///         }
+///     }
+/// }
+///
+/// fn main() {
+///     match File::parse(&*std::fs::read("foo.o").unwrap()).unwrap() {
+///         File::MachO32(file) => read(file),
+///         File::MachO64(file) => read(file),
+///         _ => unimplemented!(),
+///     }
+/// }
+/// ```
+pub(super) fn add_data_and_relocation(
+    file: &mut object::write::Object<'_>,
+    section: object::write::SectionId,
+    symbol: object::write::SymbolId,
+    target: &Target,
+) -> object::write::Result<()> {
+    let (data, align, addend, r_type): (&[u8], _, _, _) = match &*target.arch {
+        "arm" => (&[0xff, 0xf7, 0xfe, 0xbf], 2, 0, object::macho::ARM_THUMB_RELOC_BR22),
+        "aarch64" => (&[0, 0, 0, 0x14], 4, 0, object::macho::ARM64_RELOC_BRANCH26),
+        "x86_64" => (
+            &[0x55, 0x48, 0x89, 0xe5, 0x5d, 0xe9, 0, 0, 0, 0],
+            16,
+            -4,
+            object::macho::X86_64_RELOC_BRANCH,
+        ),
+        "x86" => (&[0x55, 0x89, 0xe5, 0x5d, 0xe9, 0xf7, 0xff, 0xff, 0xff], 16, -4, 0),
+        arch => unimplemented!("unsupported Apple architecture {arch:?}"),
+    };
+
+    let offset = file.section_mut(section).append_data(data, align);
+    file.add_relocation(section, object::write::Relocation {
+        offset,
+        addend,
+        symbol,
+        flags: object::write::RelocationFlags::MachO { r_type, r_pcrel: true, r_length: 2 },
+    })?;
+
+    Ok(())
+}
+
 /// Deployment target or SDK version.
 ///
 /// The size of the numbers in here are limited by Mach-O's `LC_BUILD_VERSION`.

compiler/rustc_codegen_ssa/src/back/link.rs

@@ -2070,8 +2070,20 @@ fn add_linked_symbol_object(
         file.set_mangling(object::write::Mangling::None);
     }
 
+    // ld64 requires a relocation to load undefined symbols, see below.
+    // Not strictly needed if linking with lld, but might as well do it there too.
+    let ld64_section_helper = if file.format() == object::BinaryFormat::MachO {
+        Some(file.add_section(
+            file.segment_name(object::write::StandardSegment::Text).to_vec(),
+            "__text".into(),
+            object::SectionKind::Text,
+        ))
+    } else {
+        None
+    };
+
     for (sym, kind) in symbols.iter() {
-        file.add_symbol(object::write::Symbol {
+        let symbol = file.add_symbol(object::write::Symbol {
             name: sym.clone().into(),
             value: 0,
             size: 0,
@@ -2085,6 +2097,21 @@ fn add_linked_symbol_object(
             section: object::write::SymbolSection::Undefined,
             flags: object::SymbolFlags::None,
         });
+
+        // The linker shipped with Apple's Xcode, ld64, works a bit differently from other linkers.
+        // In particular, it completely ignores undefined symbols by themselves, and only consider
+        // undefined symbols if they have relocations.
+        //
+        // So to make this trick work on ld64, we need to actually insert a relocation. The
+        // relocation must be valid though, and hence must point to a valid piece of machine code,
+        // and hence this is all very architecture-specific.
+        //
+        // See the following for a few details on the design of ld64:
+        // https://github.com/apple-oss-distributions/ld64/blob/ld64-951.9/doc/design/linker.html
+        if let Some(section) = ld64_section_helper {
+            apple::add_data_and_relocation(&mut file, section, symbol, &sess.target)
+                .expect("failed adding relocation");
+        }
     }
 
     let path = tmpdir.join("symbols.o");

tests/run-make/include-all-symbols-linking/lib.rs

@@ -1,5 +1,6 @@
 mod foo {
-    #[link_section = ".rodata.STATIC"]
+    #[cfg_attr(target_os = "linux", link_section = ".rodata.STATIC")]
+    #[cfg_attr(target_vendor = "apple", link_section = "__DATA,STATIC")]
     #[used]
     static STATIC: [u32; 10] = [1; 10];
 }

tests/run-make/include-all-symbols-linking/rmake.rs

@@ -7,15 +7,20 @@
 // See https://github.com/rust-lang/rust/pull/95604
 // See https://github.com/rust-lang/rust/issues/47384
 
-//@ only-linux
-// Reason: differences in object file formats on OSX and Windows
-// causes errors in the llvm_objdump step
+//@ ignore-windows differences in object file formats causes errors in the llvm_objdump step.
+//@ ignore-wasm differences in object file formats causes errors in the llvm_objdump step.
 
-use run_make_support::{dynamic_lib_name, llvm_objdump, llvm_readobj, rustc};
+use run_make_support::{dynamic_lib_name, llvm_objdump, llvm_readobj, rustc, target};
 
 fn main() {
     rustc().crate_type("lib").input("lib.rs").run();
-    rustc().crate_type("cdylib").link_args("-Tlinker.ld").input("main.rs").run();
+    let mut main = rustc();
+    main.crate_type("cdylib");
+    if target().contains("linux") {
+        main.link_args("-Tlinker.ld");
+    }
+    main.input("main.rs").run();
+
     // Ensure `#[used]` and `KEEP`-ed section is there
     llvm_objdump()
         .arg("--full-contents")