Embed bitcode in object file (clang cc1 part)
Summary:
Teach clang to embed bitcode inside bitcode. When -fembed-bitcode cc1
option is used, clang will embed both the input bitcode and cc1
commandline into the bitcode in special sections before compiling to
the object file. Using -fembed-bitcode-marker will only introduce a
marker in both sections.
Depends on D17390
Reviewers: rsmith
Subscribers: yaron.keren, vsk, cfe-commits
Differential Revision: http://reviews.llvm.org/D17392
llvm-svn: 269202
diff --git a/clang/lib/CodeGen/BackendUtil.cpp b/clang/lib/CodeGen/BackendUtil.cpp
index c86eeaf..6c934a8 100644
--- a/clang/lib/CodeGen/BackendUtil.cpp
+++ b/clang/lib/CodeGen/BackendUtil.cpp
@@ -16,9 +16,11 @@
#include "clang/Frontend/Utils.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringSwitch.h"
+#include "llvm/ADT/Triple.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Bitcode/BitcodeWriterPass.h"
+#include "llvm/Bitcode/ReaderWriter.h"
#include "llvm/CodeGen/RegAllocRegistry.h"
#include "llvm/CodeGen/SchedulerRegistry.h"
#include "llvm/IR/DataLayout.h"
@@ -763,3 +765,91 @@
}
}
}
+
+static const char* getSectionNameForBitcode(const Triple &T) {
+ switch (T.getObjectFormat()) {
+ case Triple::MachO:
+ return "__LLVM,__bitcode";
+ case Triple::COFF:
+ case Triple::ELF:
+ case Triple::UnknownObjectFormat:
+ return ".llvmbc";
+ }
+}
+
+static const char* getSectionNameForCommandline(const Triple &T) {
+ switch (T.getObjectFormat()) {
+ case Triple::MachO:
+ return "__LLVM,__cmdline";
+ case Triple::COFF:
+ case Triple::ELF:
+ case Triple::UnknownObjectFormat:
+ return ".llvmcmd";
+ }
+}
+
+// With -fembed-bitcode, save a copy of the llvm IR as data in the
+// __LLVM,__bitcode section.
+void clang::EmbedBitcode(llvm::Module *M, const CodeGenOptions &CGOpts,
+ llvm::MemoryBufferRef Buf) {
+ if (CGOpts.getEmbedBitcode() == CodeGenOptions::Embed_Off)
+ return;
+
+ // Embed the bitcode for the llvm module.
+ std::string Data;
+ ArrayRef<uint8_t> ModuleData;
+ Triple T(M->getTargetTriple());
+ // Create a constant that contains the bitcode.
+ // In case of embedding a marker, ignore the input Buf and use the empty
+ // ArrayRef. It is also legal to create a bitcode marker even Buf is empty.
+ if (CGOpts.getEmbedBitcode() != CodeGenOptions::Embed_Marker) {
+ if (!isBitcode((const unsigned char *)Buf.getBufferStart(),
+ (const unsigned char *)Buf.getBufferEnd())) {
+ // If the input is LLVM Assembly, bitcode is produced by serializing
+ // the module. Use-lists order need to be perserved in this case.
+ llvm::raw_string_ostream OS(Data);
+ llvm::WriteBitcodeToFile(M, OS, /* ShouldPreserveUseListOrder */ true);
+ ModuleData =
+ ArrayRef<uint8_t>((const uint8_t *)OS.str().data(), OS.str().size());
+ } else
+ // If the input is LLVM bitcode, write the input byte stream directly.
+ ModuleData = ArrayRef<uint8_t>((const uint8_t *)Buf.getBufferStart(),
+ Buf.getBufferSize());
+ }
+ llvm::Constant *ModuleConstant =
+ llvm::ConstantDataArray::get(M->getContext(), ModuleData);
+ // Use Appending linkage so it doesn't get optimized out.
+ llvm::GlobalVariable *GV = new llvm::GlobalVariable(
+ *M, ModuleConstant->getType(), true, llvm::GlobalValue::AppendingLinkage,
+ ModuleConstant);
+ GV->setSection(getSectionNameForBitcode(T));
+ if (llvm::GlobalVariable *Old =
+ M->getGlobalVariable("llvm.embedded.module")) {
+ assert(Old->use_empty() && "llvm.embedded.module must have no uses");
+ GV->takeName(Old);
+ Old->eraseFromParent();
+ } else {
+ GV->setName("llvm.embedded.module");
+ }
+
+ // Return if only bitcode needs to be embedded.
+ if (CGOpts.getEmbedBitcode() == CodeGenOptions::Embed_Bitcode)
+ return;
+
+ // Embed command-line options.
+ ArrayRef<uint8_t> CmdData((uint8_t*)CGOpts.CmdArgs.data(),
+ CGOpts.CmdArgs.size());
+ llvm::Constant *CmdConstant =
+ llvm::ConstantDataArray::get(M->getContext(), CmdData);
+ GV = new llvm::GlobalVariable(*M, CmdConstant->getType(), true,
+ llvm::GlobalValue::AppendingLinkage,
+ CmdConstant);
+ GV->setSection(getSectionNameForCommandline(T));
+ if (llvm::GlobalVariable *Old = M->getGlobalVariable("llvm.cmdline")) {
+ assert(Old->use_empty() && "llvm.cmdline must have no uses");
+ GV->takeName(Old);
+ Old->eraseFromParent();
+ } else {
+ GV->setName("llvm.cmdline");
+ }
+}
diff --git a/clang/lib/CodeGen/CodeGenAction.cpp b/clang/lib/CodeGen/CodeGenAction.cpp
index 9868553..848acb4 100644
--- a/clang/lib/CodeGen/CodeGenAction.cpp
+++ b/clang/lib/CodeGen/CodeGenAction.cpp
@@ -173,6 +173,8 @@
return;
}
+ EmbedBitcode(getModule(), CodeGenOpts, llvm::MemoryBufferRef());
+
EmitBackendOutput(Diags, CodeGenOpts, TargetOpts, LangOpts,
C.getTargetInfo().getDataLayout(),
getModule(), Action, AsmOutStream);
@@ -831,9 +833,13 @@
TheModule->setTargetTriple(TargetOpts.Triple);
}
+ EmbedBitcode(TheModule.get(), CI.getCodeGenOpts(),
+ MainFile->getMemBufferRef());
+
LLVMContext &Ctx = TheModule->getContext();
Ctx.setInlineAsmDiagnosticHandler(BitcodeInlineAsmDiagHandler,
&CI.getDiagnostics());
+
EmitBackendOutput(CI.getDiagnostics(), CI.getCodeGenOpts(), TargetOpts,
CI.getLangOpts(), CI.getTarget().getDataLayout(),
TheModule.get(), BA, OS);