llvm-lib: Disallow mixing object files with different machine types

[thakis]

Summary

lib.exe doesn't allow creating .lib files with object files that have
differing machine types. Update llvm-lib to match.

The motivation is to make it possible to infer the machine type of a
.lib file in lld, so that it can warn when e.g. a 32-bit .lib file is
passed to a 64-bit link (PR38965).

Fixes PR38782.

[thakis]

add newlines to diagnostics

[thakis]

pcc: Ping :)

[pcc]

LGTM

[plotfi]

@thakis this is breaking build bots: http://lab.llvm.org:8011/builders/clang-cmake-armv8-full/builds/12684

./build/Release/Linux-x86_64/llvm/test/Object/Output/nm-archive.test.tmp1: unknown arch in target triple

---

Testing Time: 114.29s

---

Failing Tests (1):

LLVM :: Object/nm-archive.test

[thakis]

Thanks, r362809 should help.

llvm/lib/ToolDrivers/llvm-lib/CMakeLists.txt

 set(LLVM_LINK_COMPONENTS
   BinaryFormat
+  BitReader
   Object
   Option
   Support
   )
 
 set(LLVM_TARGET_DEFINITIONS Options.td)
 tablegen(LLVM Options.inc -gen-opt-parser-defs)
 add_public_tablegen_target(LibOptionsTableGen)
 
 add_llvm_library(LLVMLibDriver
   LibDriver.cpp
   )
 add_dependencies(LLVMLibDriver LibOptionsTableGen)

llvm/lib/ToolDrivers/llvm-lib/LLVMBuild.txt

 ;   http://llvm.org/docs/LLVMBuild.html
 ;
 ;===------------------------------------------------------------------------===;
 
 [component_0]
 type = Library
 name = LibDriver
 parent = Libraries
-required_libraries = BinaryFormat Object Option Support
+required_libraries = BinaryFormat BitReader Object Option Support

llvm/lib/ToolDrivers/llvm-lib/LibDriver.cpp

 //===- LibDriver.cpp - lib.exe-compatible driver --------------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // Defines an interface to a lib.exe-compatible driver that also understands
 // bitcode files. Used by llvm-lib and lld-link /lib.
 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/ToolDrivers/llvm-lib/LibDriver.h"
 #include "llvm/ADT/STLExtras.h"
+#include "llvm/BinaryFormat/COFF.h"
 #include "llvm/BinaryFormat/Magic.h"
+#include "llvm/Bitcode/BitcodeReader.h"
 #include "llvm/Object/ArchiveWriter.h"
+#include "llvm/Object/COFF.h"
 #include "llvm/Option/Arg.h"
 #include "llvm/Option/ArgList.h"
 #include "llvm/Option/Option.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/Process.h"
 #include "llvm/Support/StringSaver.h"
 #include "llvm/Support/raw_ostream.h"
for (auto &C : Archive.children(Err)) {
     Expected<StringRef> NameOrErr = C.getName();
     fatalOpenError(NameOrErr.takeError(), B->getBufferIdentifier());
     StringRef Name = NameOrErr.get();
     llvm::outs() << Name << '\n';
   }
   fatalOpenError(std::move(Err), B->getBufferIdentifier());
 }
 
+static StringRef machineToStr(COFF::MachineTypes MT) {
+  switch (MT) {
+  case COFF::IMAGE_FILE_MACHINE_ARMNT:
+    return "arm";
+  case COFF::IMAGE_FILE_MACHINE_ARM64:
+    return "arm64";
+  case COFF::IMAGE_FILE_MACHINE_AMD64:
+    return "x64";
+  case COFF::IMAGE_FILE_MACHINE_I386:
+    return "x86";
+  default:
+    llvm_unreachable("unknown machine type");
+  }
+}
+
 int llvm::libDriverMain(ArrayRef<const char *> ArgsArr) {
   BumpPtrAllocator Alloc;
   StringSaver Saver(Alloc);
 
   // Parse command line arguments.
   SmallVector<const char *, 20> NewArgs(ArgsArr.begin(), ArgsArr.end());
   cl::ExpandResponseFiles(Saver, cl::TokenizeWindowsCommandLine, NewArgs);
   ArgsArr = NewArgs;
if (Args.hasArg(OPT_lst)) {
     doList(Args);
     return 0;
   }
 
   std::vector<StringRef> SearchPaths = getSearchPaths(&Args, Saver);
 
   // Create a NewArchiveMember for each input file.
   std::vector<NewArchiveMember> Members;
+  COFF::MachineTypes LibMachine = COFF::IMAGE_FILE_MACHINE_UNKNOWN;
   for (auto *Arg : Args.filtered(OPT_INPUT)) {
     std::string Path = findInputFile(Arg->getValue(), SearchPaths);
     if (Path.empty()) {
       llvm::errs() << Arg->getValue() << ": no such file or directory\n";
       return 1;
     }
 
     Expected<NewArchiveMember> MOrErr =
         NewArchiveMember::getFile(Saver.save(Path), /*Deterministic=*/true);
     if (!MOrErr) {
       handleAllErrors(MOrErr.takeError(), [&](const ErrorInfoBase &EIB) {
         llvm::errs() << Arg->getValue() << ": " << EIB.message() << "\n";
       });
       return 1;
     }
 
     file_magic Magic = identify_magic(MOrErr->Buf->getBuffer());
     if (Magic != file_magic::coff_object && Magic != file_magic::bitcode &&
         Magic != file_magic::windows_resource) {
       llvm::errs() << Arg->getValue()
                    << ": not a COFF object, bitcode or resource file\n";
       return 1;
     }
+
+    // Check that all input files have the same machine type.
+    // Mixing normal objects and LTO bitcode files is fine as long as they
+    // have the same machine type.
+    // Doing this here duplicates the header parsing work that writeArchive()
+    // below does, but it's not a lot of work and it's a bit awkward to do
+    // in writeArchive() which needs to support many tools, can't assume the
+    // input is COFF, and doesn't have a good way to report errors.
+    COFF::MachineTypes FileMachine = COFF::IMAGE_FILE_MACHINE_UNKNOWN;
+    if (Magic == file_magic::coff_object) {
+      std::error_code EC;
+      object::COFFObjectFile Obj(*MOrErr->Buf, EC);
+      if (EC) {
+        llvm::errs() << Arg->getValue() << ": failed to open: " << EC.message()
+                     << '\n';
+        return 1;
+      }
+      uint16_t Machine = Obj.getMachine();
+      if (Machine != COFF::IMAGE_FILE_MACHINE_I386 &&
+          Machine != COFF::IMAGE_FILE_MACHINE_AMD64 &&
+          Machine != COFF::IMAGE_FILE_MACHINE_ARMNT &&
+          Machine != COFF::IMAGE_FILE_MACHINE_ARM64) {
+        llvm::errs() << Arg->getValue() << ": unknown machine: " << Machine
+                     << '\n';
+        return 1;
+      }
+      FileMachine = static_cast<COFF::MachineTypes>(Machine);
+    } else if (Magic == file_magic::bitcode) {
+      Expected<std::string> TripleStr = getBitcodeTargetTriple(*MOrErr->Buf);
+      if (!TripleStr) {
+        llvm::errs() << Arg->getValue()
+                     << ": failed to get target triple from bitcode\n";
+        return 1;
+      }
+      switch (Triple(*TripleStr).getArch()) {
+      case Triple::x86:
+        FileMachine = COFF::IMAGE_FILE_MACHINE_I386;
+        break;
+      case Triple::x86_64:
+        FileMachine = COFF::IMAGE_FILE_MACHINE_AMD64;
+        break;
+      case Triple::arm:
+        FileMachine = COFF::IMAGE_FILE_MACHINE_ARMNT;
+        break;
+      case Triple::aarch64:
+        FileMachine = COFF::IMAGE_FILE_MACHINE_ARM64;
+        break;
+      default:
+        llvm::errs() << Arg->getValue() << ": unknown arch in target triple "
+                     << *TripleStr << '\n';
+        return 1;
+      }
+    }
+
+    if (FileMachine != COFF::IMAGE_FILE_MACHINE_UNKNOWN) {
+      if (LibMachine == COFF::IMAGE_FILE_MACHINE_UNKNOWN)
+        LibMachine = FileMachine;
+      else if (LibMachine != FileMachine) {
+        llvm::errs() << Arg->getValue() << ": file machine type "
+                     << machineToStr(FileMachine)
+                     << " conflicts with library machine type "
+                     << machineToStr(LibMachine) << '\n';
+        return 1;
+      }
+    }
+
     Members.emplace_back(std::move(*MOrErr));
   }
 
   // Create an archive file.
   std::string OutputPath = getOutputPath(&Args, Members[0]);
   // llvm-lib uses relative paths for both regular and thin archives, unlike
   // standard GNU ar, which only uses relative paths for thin archives and
   // basenames for regular archives.

llvm/test/tools/llvm-lib/Inputs/arm64.ll

+; ModuleID = 'test2.cc'
+source_filename = "test2.cc"
+target datalayout = "e-m:w-p:64:64-i32:32-i64:64-i128:128-n32:64-S128"
+target triple = "arm64-pc-windows-msvc19.11.0"
+
+; Function Attrs: noinline nounwind optnone uwtable
+define dso_local void @"?f@@YAXXZ"() #0 {
+entry:
+  ret void
+}
+
+attributes #0 = { noinline nounwind optnone uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="generic" "target-features"="+neon" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+!llvm.module.flags = !{!0}
+!llvm.ident = !{!1}
+
+!0 = !{i32 1, !"wchar_size", i32 2}
+!1 = !{!"clang version 9.0.0 "}

llvm/test/tools/llvm-lib/Inputs/i386.ll

+; ModuleID = 'test2.cc'
+source_filename = "test2.cc"
+target datalayout = "e-m:x-p:32:32-i64:64-f80:32-n8:16:32-a:0:32-S32"
+target triple = "i386-pc-windows-msvc19.11.0"
+
+; Function Attrs: noinline nounwind optnone
+define dso_local void @"?f@@YAXXZ"() #0 {
+entry:
+  ret void
+}
+
+attributes #0 = { noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="pentium4" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+!llvm.module.flags = !{!0, !1}
+!llvm.ident = !{!2}
+
+!0 = !{i32 1, !"NumRegisterParameters", i32 0}
+!1 = !{i32 1, !"wchar_size", i32 2}
+!2 = !{!"clang version 9.0.0 "}

llvm/test/tools/llvm-lib/Inputs/x86_64.ll

+; ModuleID = 'test2.cc'
+source_filename = "test2.cc"
+target datalayout = "e-m:w-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-pc-windows-msvc19.11.0"
+
+; Function Attrs: noinline nounwind optnone uwtable
+define dso_local void @"?f@@YAXXZ"() #0 {
+entry:
+  ret void
+}
+
+attributes #0 = { noinline nounwind optnone uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+!llvm.module.flags = !{!0, !1}
+!llvm.ident = !{!2}
+
+!0 = !{i32 1, !"wchar_size", i32 2}
+!1 = !{i32 7, !"PIC Level", i32 2}
+!2 = !{!"clang version 9.0.0 "}

llvm/test/tools/llvm-lib/machine-mismatch.test

+Prepare inputs:
+
+RUN: rm -rf %t && mkdir -p %t
+RUN: llvm-mc -triple=i386-pc-windows-msvc -filetype=obj -o %t/i386.obj %S/Inputs/a.s
+RUN: llvm-mc -triple=x86_64-pc-windows-msvc -filetype=obj -o %t/x86_64.obj %S/Inputs/a.s
+RUN: llvm-as -o %t/i386.bc %S/Inputs/i386.ll
+RUN: llvm-as -o %t/x86_64.bc %S/Inputs/x86_64.ll
+RUN: llvm-as -o %t/arm64.bc %S/Inputs/arm64.ll
+
+
+Mixing bitcode and normal object files with the same machine type is ok:
+
+RUN: llvm-lib %t/i386.obj %t/i386.bc
+RUN: llvm-lib %t/x86_64.obj %t/x86_64.bc
+
+
+As is including resource files:
+
+RUN: llvm-lib %S/Inputs/resource.res %t/i386.obj %t/i386.bc
+RUN: llvm-lib %t/x86_64.obj %S/Inputs/resource.res %t/x86_64.bc
+
+
+Mixing object files with different machine type is not ok:
+
+RUN: not llvm-lib %t/x86_64.obj %t/i386.obj 2>&1 | \
+RUN:     FileCheck --check-prefix=OBJ32 %s
+OBJ32: i386.obj: file machine type x86 conflicts with library machine type x64
+
+
+Neither is mixing object and bitcode files with different machine type:
+
+RUN: not llvm-lib %t/x86_64.obj %t/i386.bc 2>&1 | \
+RUN:     FileCheck --check-prefix=BC32 %s
+BC32: i386.bc: file machine type x86 conflicts with library machine type x64
+
+RUN: not llvm-lib %t/arm64.bc %t/x86_64.bc 2>&1 | \
+RUN:     FileCheck --check-prefix=BC64 %s
+BC64: x86_64.bc: file machine type x64 conflicts with library machine type arm64

llvm/utils/gn/secondary/llvm/lib/ToolDrivers/llvm-lib/BUILD.gn

 import("//llvm/utils/TableGen/tablegen.gni")
 
 tablegen("Options") {
   visibility = [ ":LibDriver" ]
   args = [ "-gen-opt-parser-defs" ]
 }
 
 static_library("LibDriver") {
   output_name = "LLVMLibDriver"
   deps = [
     ":Options",
     "//llvm/lib/BinaryFormat",
+    "//llvm/lib/Bitcode/Reader",
     "//llvm/lib/Object",
     "//llvm/lib/Option",
     "//llvm/lib/Support",
   ]
   sources = [
     "LibDriver.cpp",
   ]
 }