Rollup merge of #124033 - bjorn3:ar_archive_writer_0_3_0, r=davidtwco

Sync ar_archive_writer to LLVM 18.1.3

From LLVM 15.0.0-rc3. This adds support for COFF archives containing Arm64EC object files and has various fixes for AIX big archive files.

Cargo.lock

@@ -236,11 +236,11 @@ checksum = "d67af77d68a931ecd5cbd8a3b5987d63a1d1d1278f7f6a60ae33db485cdebb69"
 
 [[package]]
 name = "ar_archive_writer"
-version = "0.2.0"
+version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f0c269894b6fe5e9d7ada0cf69b5bf847ff35bc25fc271f08e1d080fce80339a"
+checksum = "f8412a2d690663356cba5a2532f3ed55d1e8090743bc6695b88403b27df67733"
 dependencies = [
- "object 0.32.2",
+ "object 0.35.0",
 ]
 
 [[package]]
@@ -2648,6 +2648,15 @@ dependencies = [
  "ruzstd 0.6.0",
 ]
 
+[[package]]
+name = "object"
+version = "0.35.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8ec7ab813848ba4522158d5517a6093db1ded27575b070f4177b8d12b41db5e"
+dependencies = [
+ "memchr",
+]
+
 [[package]]
 name = "object"
 version = "0.36.0"

compiler/rustc_codegen_cranelift/src/archive.rs

@@ -1,7 +1,7 @@
 use std::path::{Path, PathBuf};
 
 use rustc_codegen_ssa::back::archive::{
-    get_native_object_symbols, ArArchiveBuilder, ArchiveBuilder, ArchiveBuilderBuilder,
+    ArArchiveBuilder, ArchiveBuilder, ArchiveBuilderBuilder, DEFAULT_OBJECT_READER,
 };
 use rustc_session::Session;
 
@@ -9,7 +9,7 @@ pub(crate) struct ArArchiveBuilderBuilder;
 
 impl ArchiveBuilderBuilder for ArArchiveBuilderBuilder {
     fn new_archive_builder<'a>(&self, sess: &'a Session) -> Box<dyn ArchiveBuilder + 'a> {
-        Box::new(ArArchiveBuilder::new(sess, get_native_object_symbols))
+        Box::new(ArArchiveBuilder::new(sess, &DEFAULT_OBJECT_READER))
     }
 
     fn create_dll_import_lib(

compiler/rustc_codegen_gcc/src/archive.rs

@@ -1,7 +1,7 @@
 use std::path::{Path, PathBuf};
 
 use rustc_codegen_ssa::back::archive::{
-    get_native_object_symbols, ArArchiveBuilder, ArchiveBuilder, ArchiveBuilderBuilder,
+    ArArchiveBuilder, ArchiveBuilder, ArchiveBuilderBuilder, DEFAULT_OBJECT_READER,
 };
 use rustc_session::Session;
 
@@ -11,7 +11,7 @@ pub(crate) struct ArArchiveBuilderBuilder;
 
 impl ArchiveBuilderBuilder for ArArchiveBuilderBuilder {
     fn new_archive_builder<'a>(&self, sess: &'a Session) -> Box<dyn ArchiveBuilder + 'a> {
-        Box::new(ArArchiveBuilder::new(sess, get_native_object_symbols))
+        Box::new(ArArchiveBuilder::new(sess, &DEFAULT_OBJECT_READER))
     }
 
     fn create_dll_import_lib(

compiler/rustc_codegen_llvm/src/back/archive.rs

@@ -15,8 +15,8 @@ use crate::errors::{
 use crate::llvm::archive_ro::{ArchiveRO, Child};
 use crate::llvm::{self, ArchiveKind, LLVMMachineType, LLVMRustCOFFShortExport};
 use rustc_codegen_ssa::back::archive::{
-    get_native_object_symbols, try_extract_macho_fat_archive, ArArchiveBuilder,
-    ArchiveBuildFailure, ArchiveBuilder, ArchiveBuilderBuilder, UnknownArchiveKind,
+    try_extract_macho_fat_archive, ArArchiveBuilder, ArchiveBuildFailure, ArchiveBuilder,
+    ArchiveBuilderBuilder, ObjectReader, UnknownArchiveKind, DEFAULT_OBJECT_READER,
 };
 use tracing::trace;
 
@@ -115,7 +115,7 @@ impl ArchiveBuilderBuilder for LlvmArchiveBuilderBuilder {
         if true {
             Box::new(LlvmArchiveBuilder { sess, additions: Vec::new() })
         } else {
-            Box::new(ArArchiveBuilder::new(sess, get_llvm_object_symbols))
+            Box::new(ArArchiveBuilder::new(sess, &LLVM_OBJECT_READER))
         }
     }
 
@@ -291,57 +291,82 @@ impl ArchiveBuilderBuilder for LlvmArchiveBuilderBuilder {
 
 // The object crate doesn't know how to get symbols for LLVM bitcode and COFF bigobj files.
 // As such we need to use LLVM for them.
-#[deny(unsafe_op_in_unsafe_fn)]
-fn get_llvm_object_symbols(
-    buf: &[u8],
-    f: &mut dyn FnMut(&[u8]) -> io::Result<()>,
-) -> io::Result<bool> {
+
+static LLVM_OBJECT_READER: ObjectReader = ObjectReader {
+    get_symbols: get_llvm_object_symbols,
+    is_64_bit_object_file: llvm_is_64_bit_object_file,
+    is_ec_object_file: llvm_is_ec_object_file,
+    get_xcoff_member_alignment: DEFAULT_OBJECT_READER.get_xcoff_member_alignment,
+};
+
+fn should_use_llvm_reader(buf: &[u8]) -> bool {
     let is_bitcode = unsafe { llvm::LLVMRustIsBitcode(buf.as_ptr(), buf.len()) };
 
     // COFF bigobj file, msvc LTO file or import library. See
     // https://github.com/llvm/llvm-project/blob/453f27bc9/llvm/lib/BinaryFormat/Magic.cpp#L38-L51
     let is_unsupported_windows_obj_file = buf.get(0..4) == Some(b"\0\0\xFF\xFF");
 
-    if is_bitcode || is_unsupported_windows_obj_file {
-        let mut state = Box::new(f);
+    is_bitcode || is_unsupported_windows_obj_file
+}
 
-        let err = unsafe {
-            llvm::LLVMRustGetSymbols(
-                buf.as_ptr(),
-                buf.len(),
-                std::ptr::addr_of_mut!(*state) as *mut c_void,
-                callback,
-                error_callback,
-            )
-        };
-
-        if err.is_null() {
-            return Ok(true);
-        } else {
-            return Err(unsafe { *Box::from_raw(err as *mut io::Error) });
-        }
-
-        unsafe extern "C" fn callback(
-            state: *mut c_void,
-            symbol_name: *const c_char,
-        ) -> *mut c_void {
-            let f = unsafe { &mut *(state as *mut &mut dyn FnMut(&[u8]) -> io::Result<()>) };
-            match f(unsafe { CStr::from_ptr(symbol_name) }.to_bytes()) {
-                Ok(()) => std::ptr::null_mut(),
-                Err(err) => Box::into_raw(Box::new(err)) as *mut c_void,
-            }
-        }
-
-        unsafe extern "C" fn error_callback(error: *const c_char) -> *mut c_void {
-            let error = unsafe { CStr::from_ptr(error) };
-            Box::into_raw(Box::new(io::Error::new(
-                io::ErrorKind::Other,
-                format!("LLVM error: {}", error.to_string_lossy()),
-            ))) as *mut c_void
-        }
-    } else {
-        get_native_object_symbols(buf, f)
+#[deny(unsafe_op_in_unsafe_fn)]
+fn get_llvm_object_symbols(
+    buf: &[u8],
+    f: &mut dyn FnMut(&[u8]) -> io::Result<()>,
+) -> io::Result<bool> {
+    if !should_use_llvm_reader(buf) {
+        return (DEFAULT_OBJECT_READER.get_symbols)(buf, f);
     }
+
+    let mut state = Box::new(f);
+
+    let err = unsafe {
+        llvm::LLVMRustGetSymbols(
+            buf.as_ptr(),
+            buf.len(),
+            std::ptr::addr_of_mut!(*state) as *mut c_void,
+            callback,
+            error_callback,
+        )
+    };
+
+    if err.is_null() {
+        return Ok(true);
+    } else {
+        return Err(unsafe { *Box::from_raw(err as *mut io::Error) });
+    }
+
+    unsafe extern "C" fn callback(state: *mut c_void, symbol_name: *const c_char) -> *mut c_void {
+        let f = unsafe { &mut *(state as *mut &mut dyn FnMut(&[u8]) -> io::Result<()>) };
+        match f(unsafe { CStr::from_ptr(symbol_name) }.to_bytes()) {
+            Ok(()) => std::ptr::null_mut(),
+            Err(err) => Box::into_raw(Box::new(err)) as *mut c_void,
+        }
+    }
+
+    unsafe extern "C" fn error_callback(error: *const c_char) -> *mut c_void {
+        let error = unsafe { CStr::from_ptr(error) };
+        Box::into_raw(Box::new(io::Error::new(
+            io::ErrorKind::Other,
+            format!("LLVM error: {}", error.to_string_lossy()),
+        ))) as *mut c_void
+    }
+}
+
+fn llvm_is_64_bit_object_file(buf: &[u8]) -> bool {
+    if !should_use_llvm_reader(buf) {
+        return (DEFAULT_OBJECT_READER.is_64_bit_object_file)(buf);
+    }
+
+    unsafe { llvm::LLVMRustIs64BitSymbolicFile(buf.as_ptr(), buf.len()) }
+}
+
+fn llvm_is_ec_object_file(buf: &[u8]) -> bool {
+    if !should_use_llvm_reader(buf) {
+        return (DEFAULT_OBJECT_READER.is_ec_object_file)(buf);
+    }
+
+    unsafe { llvm::LLVMRustIsECObject(buf.as_ptr(), buf.len()) }
 }
 
 impl<'a> LlvmArchiveBuilder<'a> {

compiler/rustc_codegen_llvm/src/llvm/ffi.rs

@@ -2440,4 +2440,8 @@ extern "C" {
         callback: GetSymbolsCallback,
         error_callback: GetSymbolsErrorCallback,
     ) -> *mut c_void;
+
+    pub fn LLVMRustIs64BitSymbolicFile(buf_ptr: *const u8, buf_len: usize) -> bool;
+
+    pub fn LLVMRustIsECObject(buf_ptr: *const u8, buf_len: usize) -> bool;
 }

compiler/rustc_codegen_ssa/Cargo.toml

@@ -5,7 +5,7 @@ edition = "2021"
 
 [dependencies]
 # tidy-alphabetical-start
-ar_archive_writer = "0.2.0"
+ar_archive_writer = "0.3.0"
 arrayvec = { version = "0.7", default-features = false }
 bitflags = "2.4.1"
 cc = "1.0.90"

compiler/rustc_codegen_ssa/src/back/archive.rs

@@ -6,8 +6,8 @@ use rustc_span::symbol::Symbol;
 
 use super::metadata::search_for_section;
 
-pub use ar_archive_writer::get_native_object_symbols;
 use ar_archive_writer::{write_archive_to_stream, ArchiveKind, NewArchiveMember};
+pub use ar_archive_writer::{ObjectReader, DEFAULT_OBJECT_READER};
 use object::read::archive::ArchiveFile;
 use object::read::macho::FatArch;
 use tempfile::Builder as TempFileBuilder;
@@ -89,8 +89,7 @@ pub trait ArchiveBuilder {
 #[must_use = "must call build() to finish building the archive"]
 pub struct ArArchiveBuilder<'a> {
     sess: &'a Session,
-    get_object_symbols:
-        fn(buf: &[u8], f: &mut dyn FnMut(&[u8]) -> io::Result<()>) -> io::Result<bool>,
+    object_reader: &'static ObjectReader,
 
     src_archives: Vec<(PathBuf, Mmap)>,
     // Don't use an `HashMap` here, as the order is important. `lib.rmeta` needs
@@ -105,14 +104,8 @@ enum ArchiveEntry {
 }
 
 impl<'a> ArArchiveBuilder<'a> {
-    pub fn new(
-        sess: &'a Session,
-        get_object_symbols: fn(
-            buf: &[u8],
-            f: &mut dyn FnMut(&[u8]) -> io::Result<()>,
-        ) -> io::Result<bool>,
-    ) -> ArArchiveBuilder<'a> {
-        ArArchiveBuilder { sess, get_object_symbols, src_archives: vec![], entries: vec![] }
+    pub fn new(sess: &'a Session, object_reader: &'static ObjectReader) -> ArArchiveBuilder<'a> {
+        ArArchiveBuilder { sess, object_reader, src_archives: vec![], entries: vec![] }
     }
 }
 
@@ -267,7 +260,7 @@ impl<'a> ArArchiveBuilder<'a> {
 
             entries.push(NewArchiveMember {
                 buf: data,
-                get_symbols: self.get_object_symbols,
+                object_reader: self.object_reader,
                 member_name: String::from_utf8(entry_name).unwrap(),
                 mtime: 0,
                 uid: 0,
@@ -294,7 +287,13 @@ impl<'a> ArArchiveBuilder<'a> {
         let mut archive_tmpfile = File::create_new(&archive_tmpfile_path)
             .map_err(|err| io_error_context("couldn't create the temp file", err))?;
 
-        write_archive_to_stream(&mut archive_tmpfile, &entries, archive_kind, false)?;
+        write_archive_to_stream(
+            &mut archive_tmpfile,
+            &entries,
+            archive_kind,
+            false,
+            /* is_ec = */ self.sess.target.arch == "arm64ec",
+        )?;
 
         let any_entries = !entries.is_empty();
         drop(entries);

compiler/rustc_llvm/llvm-wrapper/SymbolWrapper.cpp

@@ -4,12 +4,16 @@
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 
 // Derived from:
-// * https://github.com/llvm/llvm-project/blob/8ef3e895ad8ab1724e2b87cabad1dacdc7a397a3/llvm/include/llvm/Object/ArchiveWriter.h
-// * https://github.com/llvm/llvm-project/blob/8ef3e895ad8ab1724e2b87cabad1dacdc7a397a3/llvm/lib/Object/ArchiveWriter.cpp
+// * https://github.com/llvm/llvm-project/blob/ef6d1ec07c693352c4a60dd58db08d2d8558f6ea/llvm/include/llvm/Object/ArchiveWriter.h
+// * https://github.com/llvm/llvm-project/blob/ef6d1ec07c693352c4a60dd58db08d2d8558f6ea/llvm/lib/Object/ArchiveWriter.cpp
 
+#include "LLVMWrapper.h"
 #include "SuppressLLVMWarnings.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/IR/LLVMContext.h"
+#include "llvm/Object/COFF.h"
+#include "llvm/Object/COFFImportFile.h"
+#include "llvm/Object/IRObjectFile.h"
 #include "llvm/Object/ObjectFile.h"
 #include <llvm/Support/raw_ostream.h>
 
@@ -34,6 +38,27 @@ static bool isArchiveSymbol(const object::BasicSymbolRef &S) {
 typedef void *(*LLVMRustGetSymbolsCallback)(void *, const char *);
 typedef void *(*LLVMRustGetSymbolsErrorCallback)(const char *);
 
+// This function is copied from ArchiveWriter.cpp.
+static Expected<std::unique_ptr<SymbolicFile>>
+getSymbolicFile(MemoryBufferRef Buf, LLVMContext &Context) {
+  const file_magic Type = identify_magic(Buf.getBuffer());
+  // Don't attempt to read non-symbolic file types.
+  if (!object::SymbolicFile::isSymbolicFile(Type, &Context))
+    return nullptr;
+  if (Type == file_magic::bitcode) {
+    auto ObjOrErr = object::SymbolicFile::createSymbolicFile(
+        Buf, file_magic::bitcode, &Context);
+    if (!ObjOrErr)
+      return ObjOrErr.takeError();
+    return std::move(*ObjOrErr);
+  } else {
+    auto ObjOrErr = object::SymbolicFile::createSymbolicFile(Buf);
+    if (!ObjOrErr)
+      return ObjOrErr.takeError();
+    return std::move(*ObjOrErr);
+  }
+}
+
 // Note: This is implemented in C++ instead of using the C api from Rust as
 // IRObjectFile doesn't implement getSymbolName, only printSymbolName, which is
 // inaccessible from the C api.
@@ -49,36 +74,16 @@ LLVMRustGetSymbols(char *BufPtr, size_t BufLen, void *State,
   // In the scenario when LLVMContext is populated SymbolicFile will contain a
   // reference to it, thus SymbolicFile should be destroyed first.
   LLVMContext Context;
-  std::unique_ptr<object::SymbolicFile> Obj;
-
-  const file_magic Type = identify_magic(Buf->getBuffer());
-  if (!object::SymbolicFile::isSymbolicFile(Type, &Context)) {
-    return 0;
-  }
-
-  if (Type == file_magic::bitcode) {
-    auto ObjOrErr = object::SymbolicFile::createSymbolicFile(
-        Buf->getMemBufferRef(), file_magic::bitcode, &Context);
-    if (!ObjOrErr) {
-      Error E = ObjOrErr.takeError();
-      SmallString<0> ErrorBuf;
-      auto Error = raw_svector_ostream(ErrorBuf);
-      Error << E << '\0';
-      return ErrorCallback(Error.str().data());
-    }
-    Obj = std::move(*ObjOrErr);
-  } else {
-    auto ObjOrErr =
-        object::SymbolicFile::createSymbolicFile(Buf->getMemBufferRef());
-    if (!ObjOrErr) {
-      Error E = ObjOrErr.takeError();
-      SmallString<0> ErrorBuf;
-      auto Error = raw_svector_ostream(ErrorBuf);
-      Error << E << '\0';
-      return ErrorCallback(Error.str().data());
-    }
-    Obj = std::move(*ObjOrErr);
+  Expected<std::unique_ptr<object::SymbolicFile>> ObjOrErr =
+      getSymbolicFile(Buf->getMemBufferRef(), Context);
+  if (!ObjOrErr) {
+    Error E = ObjOrErr.takeError();
+    SmallString<0> ErrorBuf;
+    auto Error = raw_svector_ostream(ErrorBuf);
+    Error << E << '\0';
+    return ErrorCallback(Error.str().data());
   }
+  std::unique_ptr<object::SymbolicFile> Obj = std::move(*ObjOrErr);
 
   for (const object::BasicSymbolRef &S : Obj->symbols()) {
     if (!isArchiveSymbol(S))
@@ -97,3 +102,72 @@ LLVMRustGetSymbols(char *BufPtr, size_t BufLen, void *State,
   }
   return 0;
 }
+
+// Encoding true and false as invalid pointer values
+#define TRUE_PTR (void *)1
+#define FALSE_PTR (void *)0
+
+extern "C" bool LLVMRustIs64BitSymbolicFile(char *BufPtr, size_t BufLen) {
+  std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(
+      StringRef(BufPtr, BufLen), StringRef("LLVMRustGetSymbolsObject"), false);
+  SmallString<0> SymNameBuf;
+  auto SymName = raw_svector_ostream(SymNameBuf);
+
+  // Code starting from this line is copied from s64BitSymbolicFile in
+  // ArchiveWriter.cpp.
+  // In the scenario when LLVMContext is populated SymbolicFile will contain a
+  // reference to it, thus SymbolicFile should be destroyed first.
+  LLVMContext Context;
+  Expected<std::unique_ptr<object::SymbolicFile>> ObjOrErr =
+      getSymbolicFile(Buf->getMemBufferRef(), Context);
+  if (!ObjOrErr) {
+    return false;
+  }
+  std::unique_ptr<object::SymbolicFile> Obj = std::move(*ObjOrErr);
+
+  return Obj != nullptr ? Obj->is64Bit() : false;
+}
+
+extern "C" bool LLVMRustIsECObject(char *BufPtr, size_t BufLen) {
+  std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(
+      StringRef(BufPtr, BufLen), StringRef("LLVMRustGetSymbolsObject"), false);
+  SmallString<0> SymNameBuf;
+  auto SymName = raw_svector_ostream(SymNameBuf);
+
+  // In the scenario when LLVMContext is populated SymbolicFile will contain a
+  // reference to it, thus SymbolicFile should be destroyed first.
+  LLVMContext Context;
+  Expected<std::unique_ptr<object::SymbolicFile>> ObjOrErr =
+      getSymbolicFile(Buf->getMemBufferRef(), Context);
+  if (!ObjOrErr) {
+    return false;
+  }
+  std::unique_ptr<object::SymbolicFile> Obj = std::move(*ObjOrErr);
+
+  if (Obj == nullptr) {
+    return false;
+  }
+
+  // Code starting from this line is copied from isECObject in
+  // ArchiveWriter.cpp with an extra #if to work with LLVM 17.
+  if (Obj->isCOFF())
+    return cast<llvm::object::COFFObjectFile>(&*Obj)->getMachine() !=
+           COFF::IMAGE_FILE_MACHINE_ARM64;
+
+#if LLVM_VERSION_GE(18, 0)
+  if (Obj->isCOFFImportFile())
+    return cast<llvm::object::COFFImportFile>(&*Obj)->getMachine() !=
+           COFF::IMAGE_FILE_MACHINE_ARM64;
+#endif
+
+  if (Obj->isIR()) {
+    Expected<std::string> TripleStr =
+        getBitcodeTargetTriple(Obj->getMemoryBufferRef());
+    if (!TripleStr)
+      return false;
+    Triple T(*TripleStr);
+    return T.isWindowsArm64EC() || T.getArch() == Triple::x86_64;
+  }
+
+  return false;
+}