llvm-project/llvm/lib/Remarks/BitstreamRemarkSerializer.cpp
Tobias Stadler dfbd76bda0
[Remarks] Restructure bitstream remarks to be fully standalone (#156715)
Currently there are two serialization modes for bitstream Remarks:
standalone and separate. The separate mode splits remark metadata (e.g.
the string table) from actual remark data. The metadata is written into
the object file by the AsmPrinter, while the remark data is stored in a
separate remarks file. This means we can't use bitstream remarks with
tools like opt that don't generate an object file. Also, it is confusing
to post-process bitstream remarks files, because only the standalone
files can be read by llvm-remarkutil. We always need to use dsymutil
to convert the separate files to standalone files, which only works for
MachO. It is not possible for clang/opt to directly emit bitstream
remark files in standalone mode, because the string table can only be
serialized after all remarks were emitted.

Therefore, this change completely removes the separate serialization
mode. Instead, the remark string table is now always written to the end
of the remarks file. This requires us to tell the serializer when to
finalize remark serialization. This automatically happens when the
serializer goes out of scope. However, often the remark file goes out of
scope before the serializer is destroyed. To diagnose this, I have added
an assert to alert users that they need to explicitly call
finalizeLLVMOptimizationRemarks.

This change paves the way for further improvements to the remark
infrastructure, including more tooling (e.g. #159784), size optimizations
for bitstream remarks, and more.

Pull Request: https://github.com/llvm/llvm-project/pull/156715
2025-09-22 16:41:39 +01:00

353 lines
12 KiB
C++

//===- BitstreamRemarkSerializer.cpp --------------------------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file provides the implementation of the LLVM bitstream remark serializer
// using LLVM's bitstream writer.
//
//===----------------------------------------------------------------------===//
#include "llvm/Remarks/BitstreamRemarkSerializer.h"
#include "llvm/ADT/ScopeExit.h"
#include "llvm/Remarks/Remark.h"
#include <cassert>
#include <optional>
using namespace llvm;
using namespace llvm::remarks;
BitstreamRemarkSerializerHelper::BitstreamRemarkSerializerHelper(
BitstreamRemarkContainerType ContainerType, raw_ostream &OS)
: Bitstream(OS), ContainerType(ContainerType) {}
static void setRecordName(unsigned RecordID, BitstreamWriter &Bitstream,
SmallVectorImpl<uint64_t> &R, StringRef Str) {
R.clear();
R.push_back(RecordID);
append_range(R, Str);
Bitstream.EmitRecord(bitc::BLOCKINFO_CODE_SETRECORDNAME, R);
}
static void initBlock(unsigned BlockID, BitstreamWriter &Bitstream,
SmallVectorImpl<uint64_t> &R, StringRef Str) {
R.clear();
R.push_back(BlockID);
Bitstream.EmitRecord(bitc::BLOCKINFO_CODE_SETBID, R);
R.clear();
append_range(R, Str);
Bitstream.EmitRecord(bitc::BLOCKINFO_CODE_BLOCKNAME, R);
}
void BitstreamRemarkSerializerHelper::setupMetaBlockInfo() {
// Setup the metadata block.
initBlock(META_BLOCK_ID, Bitstream, R, MetaBlockName);
// The container information.
setRecordName(RECORD_META_CONTAINER_INFO, Bitstream, R,
MetaContainerInfoName);
auto Abbrev = std::make_shared<BitCodeAbbrev>();
Abbrev->Add(BitCodeAbbrevOp(RECORD_META_CONTAINER_INFO));
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32)); // Version.
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 2)); // Type.
RecordMetaContainerInfoAbbrevID =
Bitstream.EmitBlockInfoAbbrev(META_BLOCK_ID, Abbrev);
}
void BitstreamRemarkSerializerHelper::setupMetaRemarkVersion() {
setRecordName(RECORD_META_REMARK_VERSION, Bitstream, R,
MetaRemarkVersionName);
auto Abbrev = std::make_shared<BitCodeAbbrev>();
Abbrev->Add(BitCodeAbbrevOp(RECORD_META_REMARK_VERSION));
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32)); // Version.
RecordMetaRemarkVersionAbbrevID =
Bitstream.EmitBlockInfoAbbrev(META_BLOCK_ID, Abbrev);
}
void BitstreamRemarkSerializerHelper::emitMetaRemarkVersion(
uint64_t RemarkVersion) {
// The remark version is emitted only if we emit remarks.
R.clear();
R.push_back(RECORD_META_REMARK_VERSION);
R.push_back(RemarkVersion);
Bitstream.EmitRecordWithAbbrev(RecordMetaRemarkVersionAbbrevID, R);
}
void BitstreamRemarkSerializerHelper::setupMetaStrTab() {
setRecordName(RECORD_META_STRTAB, Bitstream, R, MetaStrTabName);
auto Abbrev = std::make_shared<BitCodeAbbrev>();
Abbrev->Add(BitCodeAbbrevOp(RECORD_META_STRTAB));
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Blob)); // Raw table.
RecordMetaStrTabAbbrevID =
Bitstream.EmitBlockInfoAbbrev(META_BLOCK_ID, Abbrev);
}
void BitstreamRemarkSerializerHelper::emitMetaStrTab(
const StringTable &StrTab) {
// The string table is not emitted if we emit remarks separately.
R.clear();
R.push_back(RECORD_META_STRTAB);
// Serialize to a blob.
std::string Buf;
raw_string_ostream OS(Buf);
StrTab.serialize(OS);
StringRef Blob = OS.str();
Bitstream.EmitRecordWithBlob(RecordMetaStrTabAbbrevID, R, Blob);
}
void BitstreamRemarkSerializerHelper::setupMetaExternalFile() {
setRecordName(RECORD_META_EXTERNAL_FILE, Bitstream, R, MetaExternalFileName);
auto Abbrev = std::make_shared<BitCodeAbbrev>();
Abbrev->Add(BitCodeAbbrevOp(RECORD_META_EXTERNAL_FILE));
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Blob)); // Filename.
RecordMetaExternalFileAbbrevID =
Bitstream.EmitBlockInfoAbbrev(META_BLOCK_ID, Abbrev);
}
void BitstreamRemarkSerializerHelper::emitMetaExternalFile(StringRef Filename) {
// The external file is emitted only if we emit the separate metadata.
R.clear();
R.push_back(RECORD_META_EXTERNAL_FILE);
Bitstream.EmitRecordWithBlob(RecordMetaExternalFileAbbrevID, R, Filename);
}
void BitstreamRemarkSerializerHelper::setupRemarkBlockInfo() {
// Setup the remark block.
initBlock(REMARK_BLOCK_ID, Bitstream, R, RemarkBlockName);
// The header of a remark.
{
setRecordName(RECORD_REMARK_HEADER, Bitstream, R, RemarkHeaderName);
auto Abbrev = std::make_shared<BitCodeAbbrev>();
Abbrev->Add(BitCodeAbbrevOp(RECORD_REMARK_HEADER));
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 3)); // Type
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Remark Name
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Pass name
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // Function name
RecordRemarkHeaderAbbrevID =
Bitstream.EmitBlockInfoAbbrev(REMARK_BLOCK_ID, Abbrev);
}
// The location of a remark.
{
setRecordName(RECORD_REMARK_DEBUG_LOC, Bitstream, R, RemarkDebugLocName);
auto Abbrev = std::make_shared<BitCodeAbbrev>();
Abbrev->Add(BitCodeAbbrevOp(RECORD_REMARK_DEBUG_LOC));
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 7)); // File
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32)); // Line
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32)); // Column
RecordRemarkDebugLocAbbrevID =
Bitstream.EmitBlockInfoAbbrev(REMARK_BLOCK_ID, Abbrev);
}
// The hotness of a remark.
{
setRecordName(RECORD_REMARK_HOTNESS, Bitstream, R, RemarkHotnessName);
auto Abbrev = std::make_shared<BitCodeAbbrev>();
Abbrev->Add(BitCodeAbbrevOp(RECORD_REMARK_HOTNESS));
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // Hotness
RecordRemarkHotnessAbbrevID =
Bitstream.EmitBlockInfoAbbrev(REMARK_BLOCK_ID, Abbrev);
}
// An argument entry with a debug location attached.
{
setRecordName(RECORD_REMARK_ARG_WITH_DEBUGLOC, Bitstream, R,
RemarkArgWithDebugLocName);
auto Abbrev = std::make_shared<BitCodeAbbrev>();
Abbrev->Add(BitCodeAbbrevOp(RECORD_REMARK_ARG_WITH_DEBUGLOC));
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 7)); // Key
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 7)); // Value
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 7)); // File
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32)); // Line
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32)); // Column
RecordRemarkArgWithDebugLocAbbrevID =
Bitstream.EmitBlockInfoAbbrev(REMARK_BLOCK_ID, Abbrev);
}
// An argument entry with no debug location attached.
{
setRecordName(RECORD_REMARK_ARG_WITHOUT_DEBUGLOC, Bitstream, R,
RemarkArgWithoutDebugLocName);
auto Abbrev = std::make_shared<BitCodeAbbrev>();
Abbrev->Add(BitCodeAbbrevOp(RECORD_REMARK_ARG_WITHOUT_DEBUGLOC));
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 7)); // Key
Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 7)); // Value
RecordRemarkArgWithoutDebugLocAbbrevID =
Bitstream.EmitBlockInfoAbbrev(REMARK_BLOCK_ID, Abbrev);
}
}
void BitstreamRemarkSerializerHelper::setupBlockInfo() {
// Emit magic number.
for (const char C : ContainerMagic)
Bitstream.Emit(static_cast<unsigned>(C), 8);
Bitstream.EnterBlockInfoBlock();
auto ExitBlock = make_scope_exit([&] { Bitstream.ExitBlock(); });
// Setup the main metadata. Depending on the container type, we'll setup the
// required records next.
setupMetaBlockInfo();
switch (ContainerType) {
case BitstreamRemarkContainerType::RemarksFileExternal:
// Needs to know where the external remarks file is.
setupMetaExternalFile();
return;
case BitstreamRemarkContainerType::RemarksFile:
// Contains remarks: emit the version.
setupMetaRemarkVersion();
// Needs a string table.
setupMetaStrTab();
// Contains remarks: emit the remark abbrevs.
setupRemarkBlockInfo();
return;
}
llvm_unreachable("Unexpected BitstreamRemarkContainerType");
}
void BitstreamRemarkSerializerHelper::emitMetaBlock(
std::optional<StringRef> Filename) {
// Emit the meta block
Bitstream.EnterSubblock(META_BLOCK_ID, 3);
auto ExitBlock = make_scope_exit([&] { Bitstream.ExitBlock(); });
// The container version and type.
R.clear();
R.push_back(RECORD_META_CONTAINER_INFO);
R.push_back(CurrentContainerVersion);
R.push_back(static_cast<uint64_t>(ContainerType));
Bitstream.EmitRecordWithAbbrev(RecordMetaContainerInfoAbbrevID, R);
switch (ContainerType) {
case BitstreamRemarkContainerType::RemarksFileExternal:
assert(Filename != std::nullopt);
emitMetaExternalFile(*Filename);
return;
case BitstreamRemarkContainerType::RemarksFile:
emitMetaRemarkVersion(CurrentRemarkVersion);
return;
}
llvm_unreachable("Unexpected BitstreamRemarkContainerType");
}
void BitstreamRemarkSerializerHelper::emitLateMetaBlock(
const StringTable &StrTab) {
// Emit the late meta block (after all remarks are serialized)
Bitstream.EnterSubblock(META_BLOCK_ID, 3);
emitMetaStrTab(StrTab);
Bitstream.ExitBlock();
}
void BitstreamRemarkSerializerHelper::emitRemark(const Remark &Remark,
StringTable &StrTab) {
Bitstream.EnterSubblock(REMARK_BLOCK_ID, 4);
R.clear();
R.push_back(RECORD_REMARK_HEADER);
R.push_back(static_cast<uint64_t>(Remark.RemarkType));
R.push_back(StrTab.add(Remark.RemarkName).first);
R.push_back(StrTab.add(Remark.PassName).first);
R.push_back(StrTab.add(Remark.FunctionName).first);
Bitstream.EmitRecordWithAbbrev(RecordRemarkHeaderAbbrevID, R);
if (const std::optional<RemarkLocation> &Loc = Remark.Loc) {
R.clear();
R.push_back(RECORD_REMARK_DEBUG_LOC);
R.push_back(StrTab.add(Loc->SourceFilePath).first);
R.push_back(Loc->SourceLine);
R.push_back(Loc->SourceColumn);
Bitstream.EmitRecordWithAbbrev(RecordRemarkDebugLocAbbrevID, R);
}
if (std::optional<uint64_t> Hotness = Remark.Hotness) {
R.clear();
R.push_back(RECORD_REMARK_HOTNESS);
R.push_back(*Hotness);
Bitstream.EmitRecordWithAbbrev(RecordRemarkHotnessAbbrevID, R);
}
for (const Argument &Arg : Remark.Args) {
R.clear();
unsigned Key = StrTab.add(Arg.Key).first;
unsigned Val = StrTab.add(Arg.Val).first;
bool HasDebugLoc = Arg.Loc != std::nullopt;
R.push_back(HasDebugLoc ? RECORD_REMARK_ARG_WITH_DEBUGLOC
: RECORD_REMARK_ARG_WITHOUT_DEBUGLOC);
R.push_back(Key);
R.push_back(Val);
if (HasDebugLoc) {
R.push_back(StrTab.add(Arg.Loc->SourceFilePath).first);
R.push_back(Arg.Loc->SourceLine);
R.push_back(Arg.Loc->SourceColumn);
}
Bitstream.EmitRecordWithAbbrev(HasDebugLoc
? RecordRemarkArgWithDebugLocAbbrevID
: RecordRemarkArgWithoutDebugLocAbbrevID,
R);
}
Bitstream.ExitBlock();
}
BitstreamRemarkSerializer::BitstreamRemarkSerializer(raw_ostream &OS)
: RemarkSerializer(Format::Bitstream, OS) {
StrTab.emplace();
}
BitstreamRemarkSerializer::BitstreamRemarkSerializer(raw_ostream &OS,
StringTable StrTabIn)
: RemarkSerializer(Format::Bitstream, OS) {
StrTab = std::move(StrTabIn);
}
BitstreamRemarkSerializer::~BitstreamRemarkSerializer() { finalize(); }
void BitstreamRemarkSerializer::setup() {
if (Helper)
return;
Helper.emplace(BitstreamRemarkContainerType::RemarksFile, OS);
Helper->setupBlockInfo();
Helper->emitMetaBlock();
}
void BitstreamRemarkSerializer::finalize() {
if (!Helper)
return;
Helper->emitLateMetaBlock(*StrTab);
Helper = std::nullopt;
}
void BitstreamRemarkSerializer::emit(const Remark &Remark) {
setup();
Helper->emitRemark(Remark, *StrTab);
}
std::unique_ptr<MetaSerializer>
BitstreamRemarkSerializer::metaSerializer(raw_ostream &OS,
StringRef ExternalFilename) {
return std::make_unique<BitstreamMetaSerializer>(
OS, BitstreamRemarkContainerType::RemarksFileExternal, ExternalFilename);
}
void BitstreamMetaSerializer::emit() {
assert(Helper && "BitstreamMetaSerializer emitted multiple times");
Helper->setupBlockInfo();
Helper->emitMetaBlock(ExternalFilename);
Helper = std::nullopt;
}