From f8b51c5f90c60aceedef9ed185eeac58f501075a Mon Sep 17 00:00:00 2001 From: Reid Kleckner Date: Fri, 16 Mar 2018 20:13:32 +0000 Subject: [PATCH] [IR] Avoid the need to prefix MS C++ symbols with '\01' Now the Windows mangling modes ('w' and 'x') do not do any mangling for symbols starting with '?'. This means that clang can stop adding the hideous '\01' leading escape. This means LLVM debug logs are less likely to contain ASCII escape characters and it will be easier to copy and paste MS symbol names from IR. Finally. For non-Windows platforms, names starting with '?' still get IR mangling, so once clang stops escaping MS C++ names, we will get extra '_' prefixing on MachO. That's fine, since it is currently impossible to construct a triple that uses the MS C++ ABI in clang and emits macho object files. Differential Revision: https://reviews.llvm.org/D7775 llvm-svn: 327734 --- llvm/docs/LangRef.rst | 15 +- llvm/docs/ReleaseNotes.rst | 3 + llvm/include/llvm/IR/DataLayout.h | 6 + llvm/lib/IR/Mangler.cpp | 12 +- llvm/test/CodeGen/X86/mangle-question-mark.ll | 60 ++++++++ llvm/test/MC/COFF/symbol-mangling.ll | 17 --- llvm/unittests/IR/CMakeLists.txt | 1 + llvm/unittests/IR/ManglerTest.cpp | 140 ++++++++++++++++++ 8 files changed, 230 insertions(+), 24 deletions(-) create mode 100644 llvm/test/CodeGen/X86/mangle-question-mark.ll delete mode 100644 llvm/test/MC/COFF/symbol-mangling.ll create mode 100644 llvm/unittests/IR/ManglerTest.cpp diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst index 9d8242f29d73..5bbbf32710d3 100644 --- a/llvm/docs/LangRef.rst +++ b/llvm/docs/LangRef.rst @@ -1940,17 +1940,22 @@ as follows: ``a::`` This specifies the alignment for an object of aggregate type. ``m:`` - If present, specifies that llvm names are mangled in the output. The + If present, specifies that llvm names are mangled in the output. Symbols + prefixed with the mangling escape character ``\01`` are passed through + directly to the assembler without the escape character. The mangling style options are * ``e``: ELF mangling: Private symbols get a ``.L`` prefix. * ``m``: Mips mangling: Private symbols get a ``$`` prefix. * ``o``: Mach-O mangling: Private symbols get ``L`` prefix. Other symbols get a ``_`` prefix. - * ``w``: Windows COFF prefix: Similar to Mach-O, but stdcall and fastcall - functions also get a suffix based on the frame size. - * ``x``: Windows x86 COFF prefix: Similar to Windows COFF, but use a ``_`` - prefix for ``__cdecl`` functions. + * ``x``: Windows x86 COFF mangling: Private symbols get the usual prefix. + Regular C symbols get a ``_`` prefix. Functions with ``__stdcall``, + ``__fastcall``, and ``__vectorcall`` have custom mangling that appends + ``@N`` where N is the number of bytes used to pass parameters. C++ symbols + starting with ``?`` are not mangled in any way. + * ``w``: Windows COFF mangling: Similar to ``x``, except that normal C + symbols do not receive a ``_`` prefix. ``n::...`` This specifies a set of native integer widths for the target CPU in bits. For example, it might contain ``n32`` for 32-bit PowerPC, diff --git a/llvm/docs/ReleaseNotes.rst b/llvm/docs/ReleaseNotes.rst index 53d3abec9561..1deeb650e7d2 100644 --- a/llvm/docs/ReleaseNotes.rst +++ b/llvm/docs/ReleaseNotes.rst @@ -42,6 +42,9 @@ Non-comprehensive list of changes in this release * The LoopInstSimplify pass (-loop-instsimplify) has been removed. +* Symbols starting with ``?`` are no longer mangled by LLVM when using the + Windows ``x`` or ``w`` IR mangling schemes. + * Note.. .. NOTE diff --git a/llvm/include/llvm/IR/DataLayout.h b/llvm/include/llvm/IR/DataLayout.h index 00eb95231529..c48e140f3a61 100644 --- a/llvm/include/llvm/IR/DataLayout.h +++ b/llvm/include/llvm/IR/DataLayout.h @@ -263,6 +263,12 @@ public: return ManglingMode == MM_WinCOFFX86; } + /// Returns true if symbols with leading question marks should not receive IR + /// mangling. True for Windows mangling modes. + bool doNotMangleLeadingQuestionMark() const { + return ManglingMode == MM_WinCOFF || ManglingMode == MM_WinCOFFX86; + } + bool hasLinkerPrivateGlobalPrefix() const { return ManglingMode == MM_MachO; } StringRef getLinkerPrivateGlobalPrefix() const { diff --git a/llvm/lib/IR/Mangler.cpp b/llvm/lib/IR/Mangler.cpp index 7adcc59f571e..be3086cfcf05 100644 --- a/llvm/lib/IR/Mangler.cpp +++ b/llvm/lib/IR/Mangler.cpp @@ -44,6 +44,9 @@ static void getNameWithPrefixImpl(raw_ostream &OS, const Twine &GVName, return; } + if (DL.doNotMangleLeadingQuestionMark() && Name[0] == '?') + Prefix = '\0'; + if (PrefixTy == Private) OS << DL.getPrivateGlobalPrefix(); else if (PrefixTy == LinkerPrivate) @@ -135,8 +138,13 @@ void Mangler::getNameWithPrefix(raw_ostream &OS, const GlobalValue *GV, // Mangle functions with Microsoft calling conventions specially. Only do // this mangling for x86_64 vectorcall and 32-bit x86. const Function *MSFunc = dyn_cast(GV); - if (Name.startswith("\01")) - MSFunc = nullptr; // Don't mangle when \01 is present. + + // Don't add byte count suffixes when '\01' or '?' are in the first + // character. + if (Name.startswith("\01") || + (DL.doNotMangleLeadingQuestionMark() && Name.startswith("?"))) + MSFunc = nullptr; + CallingConv::ID CC = MSFunc ? MSFunc->getCallingConv() : (unsigned)CallingConv::C; if (!DL.hasMicrosoftFastStdCallMangling() && diff --git a/llvm/test/CodeGen/X86/mangle-question-mark.ll b/llvm/test/CodeGen/X86/mangle-question-mark.ll new file mode 100644 index 000000000000..582f65d39879 --- /dev/null +++ b/llvm/test/CodeGen/X86/mangle-question-mark.ll @@ -0,0 +1,60 @@ +; Test that symbols starting with '?' are not affected by IR mangling. + +; RUN: llc -mtriple i686-pc-win32 < %s | FileCheck %s --check-prefix=COFF +; RUN: llc -mtriple x86_64-pc-win32 < %s | FileCheck %s --check-prefix=COFF64 +; RUN: llc -mtriple i686-linux-gnu < %s | FileCheck %s --check-prefix=ELF +; RUN: llc -mtriple i686-apple-darwin < %s | FileCheck %s --check-prefix=MACHO + +; Currently all object files allow escaping private symbols, but eventually we +; might want to reject that. + +; COFF: calll "?withescape@A@@QBEXXZ" +; COFF: calll "?withquestion@A@@QBEXXZ" +; COFF: calll "L?privatequestion@A@@QBEXXZ" +; COFF: calll "L?privatequestionfast@A@@QBEXXZ" +; COFF: calll "?escapedprivate@A@@QBEXXZ" + +; COFF64: callq "?withescape@A@@QBEXXZ" +; COFF64: callq "?withquestion@A@@QBEXXZ" +; COFF64: callq ".L?privatequestion@A@@QBEXXZ" +; COFF64: callq ".L?privatequestionfast@A@@QBEXXZ" +; COFF64: callq "?escapedprivate@A@@QBEXXZ" + +; ELF: calll "?withescape@A@@QBEXXZ" +; ELF: calll "?withquestion@A@@QBEXXZ" +; ELF: calll ".L?privatequestion@A@@QBEXXZ" +; ELF: calll ".L?privatequestionfast@A@@QBEXXZ" +; ELF: calll "?escapedprivate@A@@QBEXXZ" + +; MACHO: calll "?withescape@A@@QBEXXZ" +; MACHO: calll "_?withquestion@A@@QBEXXZ" +; MACHO: calll "l_?privatequestion@A@@QBEXXZ" +; MACHO: calll "l_?privatequestionfast@A@@QBEXXZ" +; MACHO: calll "?escapedprivate@A@@QBEXXZ" + +%struct.A = type {} + +define i32 @main() { +entry: + tail call void @"\01?withescape@A@@QBEXXZ"(%struct.A* null) + tail call void @"?withquestion@A@@QBEXXZ"(%struct.A* null) + tail call void @"?privatequestion@A@@QBEXXZ"(%struct.A* null) + tail call x86_fastcallcc void @"?privatequestionfast@A@@QBEXXZ"(%struct.A* null) + tail call void @"\01?escapedprivate@A@@QBEXXZ"(%struct.A* null) + ret i32 0 +} + +declare void @"\01?withescape@A@@QBEXXZ"(%struct.A*) +declare void @"?withquestion@A@@QBEXXZ"(%struct.A*) + +define private void @"?privatequestion@A@@QBEXXZ"(%struct.A*) { + ret void +} + +define private x86_fastcallcc void @"?privatequestionfast@A@@QBEXXZ"(%struct.A*) { + ret void +} + +define private void @"\01?escapedprivate@A@@QBEXXZ"(%struct.A*) { + ret void +} diff --git a/llvm/test/MC/COFF/symbol-mangling.ll b/llvm/test/MC/COFF/symbol-mangling.ll deleted file mode 100644 index f1b4b4becd0e..000000000000 --- a/llvm/test/MC/COFF/symbol-mangling.ll +++ /dev/null @@ -1,17 +0,0 @@ -; The purpose of this test is to see if the MC layer properly handles symbol -; names needing quoting on MS/Windows. This code is generated by clang when -; using -cxx-abi microsoft. - -; RUN: llc -filetype=asm -mtriple i686-pc-win32 %s -o - | FileCheck %s - -; CHECK: ?sayhi@A@@QBEXXZ - -%struct.A = type {} - -define i32 @main() { -entry: - tail call void @"\01?sayhi@A@@QBEXXZ"(%struct.A* null) - ret i32 0 -} - -declare void @"\01?sayhi@A@@QBEXXZ"(%struct.A*) diff --git a/llvm/unittests/IR/CMakeLists.txt b/llvm/unittests/IR/CMakeLists.txt index 15f869c6bd41..b2782a930f8f 100644 --- a/llvm/unittests/IR/CMakeLists.txt +++ b/llvm/unittests/IR/CMakeLists.txt @@ -25,6 +25,7 @@ set(IRSources IntrinsicsTest.cpp LegacyPassManagerTest.cpp MDBuilderTest.cpp + ManglerTest.cpp MetadataTest.cpp ModuleTest.cpp PassManagerTest.cpp diff --git a/llvm/unittests/IR/ManglerTest.cpp b/llvm/unittests/IR/ManglerTest.cpp new file mode 100644 index 000000000000..04f1ca6cf977 --- /dev/null +++ b/llvm/unittests/IR/ManglerTest.cpp @@ -0,0 +1,140 @@ +//===- llvm/unittest/IR/ManglerTest.cpp - Mangler unit tests --------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#include "llvm/IR/Mangler.h" +#include "llvm/IR/CallingConv.h" +#include "llvm/IR/DataLayout.h" +#include "llvm/IR/GlobalValue.h" +#include "llvm/IR/Module.h" +#include "gtest/gtest.h" + +using namespace llvm; + +static std::string mangleStr(StringRef IRName, Mangler &Mang, + const DataLayout &DL) { + std::string Mangled; + raw_string_ostream SS(Mangled); + Mang.getNameWithPrefix(SS, IRName, DL); + SS.flush(); + return Mangled; +} + +static std::string mangleFunc(StringRef IRName, + GlobalValue::LinkageTypes Linkage, + llvm::CallingConv::ID CC, Module &Mod, + Mangler &Mang) { + Type *VoidTy = Type::getVoidTy(Mod.getContext()); + Type *I32Ty = Type::getInt32Ty(Mod.getContext()); + FunctionType *FTy = + FunctionType::get(VoidTy, {I32Ty, I32Ty, I32Ty}, /*isVarArg=*/false); + Function *F = Function::Create(FTy, Linkage, IRName, &Mod); + F->setCallingConv(CC); + std::string Mangled; + raw_string_ostream SS(Mangled); + Mang.getNameWithPrefix(SS, F, false); + SS.flush(); + F->eraseFromParent(); + return Mangled; +} + +namespace { + +TEST(ManglerTest, MachO) { + LLVMContext Ctx; + DataLayout DL("m:o"); // macho + Module Mod("test", Ctx); + Mod.setDataLayout(DL); + Mangler Mang; + EXPECT_EQ(mangleStr("foo", Mang, DL), "_foo"); + EXPECT_EQ(mangleStr("\01foo", Mang, DL), "foo"); + EXPECT_EQ(mangleStr("?foo", Mang, DL), "_?foo"); + EXPECT_EQ(mangleFunc("foo", llvm::GlobalValue::ExternalLinkage, + llvm::CallingConv::C, Mod, Mang), + "_foo"); + EXPECT_EQ(mangleFunc("?foo", llvm::GlobalValue::ExternalLinkage, + llvm::CallingConv::C, Mod, Mang), + "_?foo"); + EXPECT_EQ(mangleFunc("foo", llvm::GlobalValue::PrivateLinkage, + llvm::CallingConv::C, Mod, Mang), + "L_foo"); +} + +TEST(ManglerTest, WindowsX86) { + LLVMContext Ctx; + DataLayout DL("m:x-p:32:32"); // 32-bit windows + Module Mod("test", Ctx); + Mod.setDataLayout(DL); + Mangler Mang; + EXPECT_EQ(mangleStr("foo", Mang, DL), "_foo"); + EXPECT_EQ(mangleStr("\01foo", Mang, DL), "foo"); + EXPECT_EQ(mangleStr("?foo", Mang, DL), "?foo"); + EXPECT_EQ(mangleFunc("foo", llvm::GlobalValue::ExternalLinkage, + llvm::CallingConv::C, Mod, Mang), + "_foo"); + EXPECT_EQ(mangleFunc("?foo", llvm::GlobalValue::ExternalLinkage, + llvm::CallingConv::C, Mod, Mang), + "?foo"); + EXPECT_EQ(mangleFunc("foo", llvm::GlobalValue::PrivateLinkage, + llvm::CallingConv::C, Mod, Mang), + "L_foo"); + + // Test calling conv mangling. + EXPECT_EQ(mangleFunc("stdcall", llvm::GlobalValue::ExternalLinkage, + llvm::CallingConv::X86_StdCall, Mod, Mang), + "_stdcall@12"); + EXPECT_EQ(mangleFunc("fastcall", llvm::GlobalValue::ExternalLinkage, + llvm::CallingConv::X86_FastCall, Mod, Mang), + "@fastcall@12"); + EXPECT_EQ(mangleFunc("vectorcall", llvm::GlobalValue::ExternalLinkage, + llvm::CallingConv::X86_VectorCall, Mod, Mang), + "vectorcall@@12"); + + // Adding a '?' prefix blocks calling convention mangling. + EXPECT_EQ(mangleFunc("?fastcall", llvm::GlobalValue::ExternalLinkage, + llvm::CallingConv::X86_FastCall, Mod, Mang), + "?fastcall"); +} + +TEST(ManglerTest, WindowsX64) { + LLVMContext Ctx; + DataLayout DL("m:w-p:64:64"); // windows + Module Mod("test", Ctx); + Mod.setDataLayout(DL); + Mangler Mang; + EXPECT_EQ(mangleStr("foo", Mang, DL), "foo"); + EXPECT_EQ(mangleStr("\01foo", Mang, DL), "foo"); + EXPECT_EQ(mangleStr("?foo", Mang, DL), "?foo"); + EXPECT_EQ(mangleFunc("foo", llvm::GlobalValue::ExternalLinkage, + llvm::CallingConv::C, Mod, Mang), + "foo"); + EXPECT_EQ(mangleFunc("?foo", llvm::GlobalValue::ExternalLinkage, + llvm::CallingConv::C, Mod, Mang), + "?foo"); + EXPECT_EQ(mangleFunc("foo", llvm::GlobalValue::PrivateLinkage, + llvm::CallingConv::C, Mod, Mang), + ".Lfoo"); + + // Test calling conv mangling. + EXPECT_EQ(mangleFunc("stdcall", llvm::GlobalValue::ExternalLinkage, + llvm::CallingConv::X86_StdCall, Mod, Mang), + "stdcall"); + EXPECT_EQ(mangleFunc("fastcall", llvm::GlobalValue::ExternalLinkage, + llvm::CallingConv::X86_FastCall, Mod, Mang), + "fastcall"); + EXPECT_EQ(mangleFunc("vectorcall", llvm::GlobalValue::ExternalLinkage, + llvm::CallingConv::X86_VectorCall, Mod, Mang), + "vectorcall@@24"); + + // Adding a '?' prefix blocks calling convention mangling. + EXPECT_EQ(mangleFunc("?vectorcall", llvm::GlobalValue::ExternalLinkage, + llvm::CallingConv::X86_VectorCall, Mod, Mang), + "?vectorcall"); +} + +} // end anonymous namespace