[LTO] Support for embedding bitcode section during LTO

Summary:
This adds support for embedding bitcode in a binary during LTO. The libLTO gains supports the `-lto-embed-bitcode` flag. The option allows users of the LTO library to embed a bitcode section. For example, LLD can pass the option via `ld.lld -mllvm=-lto-embed-bitcode`.

This feature allows doing something comparable to `clang -c -fembed-bitcode`, but on the (LTO) linker level. Having bitcode alongside native code has many use-cases. To give an example, the MacOS linker can create a `-bitcode_bundle` section containing bitcode. Also, having this feature built into LLVM is an alternative to 3rd party tools such as [[ https://github.com/travitch/whole-program-llvm | wllvm ]] or [[ https://github.com/SRI-CSL/gllvm | gllvm ]]. As with these tools, this feature simplifies creating "whole-program" llvm bitcode files, but in contrast to wllvm/gllvm it does not rely on a specific llvm frontend/driver.

Patch by Josef Eisl <josef.eisl@oracle.com>

Reviewers: #llvm, #clang, rsmith, pcc, alexshap, tejohnson

Reviewed By: tejohnson

Subscribers: tejohnson, mehdi_amini, inglorion, hiraditya, aheejin, steven_wu, dexonsmith, dang, cfe-commits, llvm-commits, #llvm, #clang

Tags: #clang, #llvm

Differential Revision: https://reviews.llvm.org/D68213

1 files changed, 124 insertions, 1 deletions

diff --git a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
index fca2cc2c300..dcff7c421fc 100644
--- a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -24,9 +24,10 @@
 #include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/Triple.h"
+#include "llvm/Bitcode/BitcodeReader.h"
+#include "llvm/Bitcode/LLVMBitCodes.h"
 #include "llvm/Bitstream/BitCodes.h"
 #include "llvm/Bitstream/BitstreamWriter.h"
-#include "llvm/Bitcode/LLVMBitCodes.h"
 #include "llvm/Config/llvm-config.h"
 #include "llvm/IR/Attributes.h"
 #include "llvm/IR/BasicBlock.h"
@@ -4677,3 +4678,125 @@ void llvm::WriteThinLinkBitcodeToFile(const Module &M, raw_ostream &Out,
 
   Out.write((char *)&Buffer.front(), Buffer.size());
 }
+
+static const char *getSectionNameForBitcode(const Triple &T) {
+  switch (T.getObjectFormat()) {
+  case Triple::MachO:
+    return "__LLVM,__bitcode";
+  case Triple::COFF:
+  case Triple::ELF:
+  case Triple::Wasm:
+  case Triple::UnknownObjectFormat:
+    return ".llvmbc";
+  case Triple::XCOFF:
+    llvm_unreachable("XCOFF is not yet implemented");
+    break;
+  }
+  llvm_unreachable("Unimplemented ObjectFormatType");
+}
+
+static const char *getSectionNameForCommandline(const Triple &T) {
+  switch (T.getObjectFormat()) {
+  case Triple::MachO:
+    return "__LLVM,__cmdline";
+  case Triple::COFF:
+  case Triple::ELF:
+  case Triple::Wasm:
+  case Triple::UnknownObjectFormat:
+    return ".llvmcmd";
+  case Triple::XCOFF:
+    llvm_unreachable("XCOFF is not yet implemented");
+    break;
+  }
+  llvm_unreachable("Unimplemented ObjectFormatType");
+}
+
+void llvm::EmbedBitcodeInModule(llvm::Module &M, llvm::MemoryBufferRef Buf,
+                                bool EmbedBitcode, bool EmbedMarker,
+                                const std::vector<uint8_t> *CmdArgs) {
+  // Save llvm.compiler.used and remove it.
+  SmallVector<Constant *, 2> UsedArray;
+  SmallPtrSet<GlobalValue *, 4> UsedGlobals;
+  Type *UsedElementType = Type::getInt8Ty(M.getContext())->getPointerTo(0);
+  GlobalVariable *Used = collectUsedGlobalVariables(M, UsedGlobals, true);
+  for (auto *GV : UsedGlobals) {
+    if (GV->getName() != "llvm.embedded.module" &&
+        GV->getName() != "llvm.cmdline")
+      UsedArray.push_back(
+          ConstantExpr::getPointerBitCastOrAddrSpaceCast(GV, UsedElementType));
+  }
+  if (Used)
+    Used->eraseFromParent();
+
+  // 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 (EmbedBitcode) {
+    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 preserved 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);
+  llvm::GlobalVariable *GV = new llvm::GlobalVariable(
+      M, ModuleConstant->getType(), true, llvm::GlobalValue::PrivateLinkage,
+      ModuleConstant);
+  GV->setSection(getSectionNameForBitcode(T));
+  UsedArray.push_back(
+      ConstantExpr::getPointerBitCastOrAddrSpaceCast(GV, UsedElementType));
+  if (llvm::GlobalVariable *Old =
+          M.getGlobalVariable("llvm.embedded.module", true)) {
+    assert(Old->hasOneUse() &&
+           "llvm.embedded.module can only be used once in llvm.compiler.used");
+    GV->takeName(Old);
+    Old->eraseFromParent();
+  } else {
+    GV->setName("llvm.embedded.module");
+  }
+
+  // Skip if only bitcode needs to be embedded.
+  if (EmbedMarker) {
+    // Embed command-line options.
+    ArrayRef<uint8_t> CmdData(const_cast<uint8_t *>(CmdArgs->data()),
+                              CmdArgs->size());
+    llvm::Constant *CmdConstant =
+        llvm::ConstantDataArray::get(M.getContext(), CmdData);
+    GV = new llvm::GlobalVariable(M, CmdConstant->getType(), true,
+                                  llvm::GlobalValue::PrivateLinkage,
+                                  CmdConstant);
+    GV->setSection(getSectionNameForCommandline(T));
+    UsedArray.push_back(
+        ConstantExpr::getPointerBitCastOrAddrSpaceCast(GV, UsedElementType));
+    if (llvm::GlobalVariable *Old = M.getGlobalVariable("llvm.cmdline", true)) {
+      assert(Old->hasOneUse() &&
+             "llvm.cmdline can only be used once in llvm.compiler.used");
+      GV->takeName(Old);
+      Old->eraseFromParent();
+    } else {
+      GV->setName("llvm.cmdline");
+    }
+  }
+
+  if (UsedArray.empty())
+    return;
+
+  // Recreate llvm.compiler.used.
+  ArrayType *ATy = ArrayType::get(UsedElementType, UsedArray.size());
+  auto *NewUsed = new GlobalVariable(
+      M, ATy, false, llvm::GlobalValue::AppendingLinkage,
+      llvm::ConstantArray::get(ATy, UsedArray), "llvm.compiler.used");
+  NewUsed->setSection("llvm.metadata");
+}