forked from OSchip/llvm-project
1708 lines
55 KiB
C++
1708 lines
55 KiB
C++
//===- SampleProfReader.cpp - Read LLVM sample profile data ---------------===//
|
|
//
|
|
// 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 implements the class that reads LLVM sample profiles. It
|
|
// supports three file formats: text, binary and gcov.
|
|
//
|
|
// The textual representation is useful for debugging and testing purposes. The
|
|
// binary representation is more compact, resulting in smaller file sizes.
|
|
//
|
|
// The gcov encoding is the one generated by GCC's AutoFDO profile creation
|
|
// tool (https://github.com/google/autofdo)
|
|
//
|
|
// All three encodings can be used interchangeably as an input sample profile.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "llvm/ProfileData/SampleProfReader.h"
|
|
#include "llvm/ADT/DenseMap.h"
|
|
#include "llvm/ADT/STLExtras.h"
|
|
#include "llvm/ADT/StringRef.h"
|
|
#include "llvm/IR/ProfileSummary.h"
|
|
#include "llvm/ProfileData/ProfileCommon.h"
|
|
#include "llvm/ProfileData/SampleProf.h"
|
|
#include "llvm/Support/Compression.h"
|
|
#include "llvm/Support/ErrorOr.h"
|
|
#include "llvm/Support/LEB128.h"
|
|
#include "llvm/Support/LineIterator.h"
|
|
#include "llvm/Support/MD5.h"
|
|
#include "llvm/Support/MemoryBuffer.h"
|
|
#include "llvm/Support/raw_ostream.h"
|
|
#include <algorithm>
|
|
#include <cstddef>
|
|
#include <cstdint>
|
|
#include <limits>
|
|
#include <memory>
|
|
#include <set>
|
|
#include <system_error>
|
|
#include <vector>
|
|
|
|
using namespace llvm;
|
|
using namespace sampleprof;
|
|
|
|
/// Dump the function profile for \p FName.
|
|
///
|
|
/// \param FName Name of the function to print.
|
|
/// \param OS Stream to emit the output to.
|
|
void SampleProfileReader::dumpFunctionProfile(StringRef FName,
|
|
raw_ostream &OS) {
|
|
OS << "Function: " << FName << ": " << Profiles[FName];
|
|
}
|
|
|
|
/// Dump all the function profiles found on stream \p OS.
|
|
void SampleProfileReader::dump(raw_ostream &OS) {
|
|
for (const auto &I : Profiles)
|
|
dumpFunctionProfile(I.getKey(), OS);
|
|
}
|
|
|
|
/// Parse \p Input as function head.
|
|
///
|
|
/// Parse one line of \p Input, and update function name in \p FName,
|
|
/// function's total sample count in \p NumSamples, function's entry
|
|
/// count in \p NumHeadSamples.
|
|
///
|
|
/// \returns true if parsing is successful.
|
|
static bool ParseHead(const StringRef &Input, StringRef &FName,
|
|
uint64_t &NumSamples, uint64_t &NumHeadSamples) {
|
|
if (Input[0] == ' ')
|
|
return false;
|
|
size_t n2 = Input.rfind(':');
|
|
size_t n1 = Input.rfind(':', n2 - 1);
|
|
FName = Input.substr(0, n1);
|
|
if (Input.substr(n1 + 1, n2 - n1 - 1).getAsInteger(10, NumSamples))
|
|
return false;
|
|
if (Input.substr(n2 + 1).getAsInteger(10, NumHeadSamples))
|
|
return false;
|
|
return true;
|
|
}
|
|
|
|
/// Returns true if line offset \p L is legal (only has 16 bits).
|
|
static bool isOffsetLegal(unsigned L) { return (L & 0xffff) == L; }
|
|
|
|
/// Parse \p Input that contains metadata.
|
|
/// Possible metadata:
|
|
/// - CFG Checksum information:
|
|
/// !CFGChecksum: 12345
|
|
/// - CFG Checksum information:
|
|
/// !Attributes: 1
|
|
/// Stores the FunctionHash (a.k.a. CFG Checksum) into \p FunctionHash.
|
|
static bool parseMetadata(const StringRef &Input, uint64_t &FunctionHash,
|
|
uint32_t &Attributes) {
|
|
if (Input.startswith("!CFGChecksum:")) {
|
|
StringRef CFGInfo = Input.substr(strlen("!CFGChecksum:")).trim();
|
|
return !CFGInfo.getAsInteger(10, FunctionHash);
|
|
}
|
|
|
|
if (Input.startswith("!Attributes:")) {
|
|
StringRef Attrib = Input.substr(strlen("!Attributes:")).trim();
|
|
return !Attrib.getAsInteger(10, Attributes);
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
enum class LineType {
|
|
CallSiteProfile,
|
|
BodyProfile,
|
|
Metadata,
|
|
};
|
|
|
|
/// Parse \p Input as line sample.
|
|
///
|
|
/// \param Input input line.
|
|
/// \param LineTy Type of this line.
|
|
/// \param Depth the depth of the inline stack.
|
|
/// \param NumSamples total samples of the line/inlined callsite.
|
|
/// \param LineOffset line offset to the start of the function.
|
|
/// \param Discriminator discriminator of the line.
|
|
/// \param TargetCountMap map from indirect call target to count.
|
|
/// \param FunctionHash the function's CFG hash, used by pseudo probe.
|
|
///
|
|
/// returns true if parsing is successful.
|
|
static bool ParseLine(const StringRef &Input, LineType &LineTy, uint32_t &Depth,
|
|
uint64_t &NumSamples, uint32_t &LineOffset,
|
|
uint32_t &Discriminator, StringRef &CalleeName,
|
|
DenseMap<StringRef, uint64_t> &TargetCountMap,
|
|
uint64_t &FunctionHash, uint32_t &Attributes) {
|
|
for (Depth = 0; Input[Depth] == ' '; Depth++)
|
|
;
|
|
if (Depth == 0)
|
|
return false;
|
|
|
|
if (Depth == 1 && Input[Depth] == '!') {
|
|
LineTy = LineType::Metadata;
|
|
return parseMetadata(Input.substr(Depth), FunctionHash, Attributes);
|
|
}
|
|
|
|
size_t n1 = Input.find(':');
|
|
StringRef Loc = Input.substr(Depth, n1 - Depth);
|
|
size_t n2 = Loc.find('.');
|
|
if (n2 == StringRef::npos) {
|
|
if (Loc.getAsInteger(10, LineOffset) || !isOffsetLegal(LineOffset))
|
|
return false;
|
|
Discriminator = 0;
|
|
} else {
|
|
if (Loc.substr(0, n2).getAsInteger(10, LineOffset))
|
|
return false;
|
|
if (Loc.substr(n2 + 1).getAsInteger(10, Discriminator))
|
|
return false;
|
|
}
|
|
|
|
StringRef Rest = Input.substr(n1 + 2);
|
|
if (isDigit(Rest[0])) {
|
|
LineTy = LineType::BodyProfile;
|
|
size_t n3 = Rest.find(' ');
|
|
if (n3 == StringRef::npos) {
|
|
if (Rest.getAsInteger(10, NumSamples))
|
|
return false;
|
|
} else {
|
|
if (Rest.substr(0, n3).getAsInteger(10, NumSamples))
|
|
return false;
|
|
}
|
|
// Find call targets and their sample counts.
|
|
// Note: In some cases, there are symbols in the profile which are not
|
|
// mangled. To accommodate such cases, use colon + integer pairs as the
|
|
// anchor points.
|
|
// An example:
|
|
// _M_construct<char *>:1000 string_view<std::allocator<char> >:437
|
|
// ":1000" and ":437" are used as anchor points so the string above will
|
|
// be interpreted as
|
|
// target: _M_construct<char *>
|
|
// count: 1000
|
|
// target: string_view<std::allocator<char> >
|
|
// count: 437
|
|
while (n3 != StringRef::npos) {
|
|
n3 += Rest.substr(n3).find_first_not_of(' ');
|
|
Rest = Rest.substr(n3);
|
|
n3 = Rest.find_first_of(':');
|
|
if (n3 == StringRef::npos || n3 == 0)
|
|
return false;
|
|
|
|
StringRef Target;
|
|
uint64_t count, n4;
|
|
while (true) {
|
|
// Get the segment after the current colon.
|
|
StringRef AfterColon = Rest.substr(n3 + 1);
|
|
// Get the target symbol before the current colon.
|
|
Target = Rest.substr(0, n3);
|
|
// Check if the word after the current colon is an integer.
|
|
n4 = AfterColon.find_first_of(' ');
|
|
n4 = (n4 != StringRef::npos) ? n3 + n4 + 1 : Rest.size();
|
|
StringRef WordAfterColon = Rest.substr(n3 + 1, n4 - n3 - 1);
|
|
if (!WordAfterColon.getAsInteger(10, count))
|
|
break;
|
|
|
|
// Try to find the next colon.
|
|
uint64_t n5 = AfterColon.find_first_of(':');
|
|
if (n5 == StringRef::npos)
|
|
return false;
|
|
n3 += n5 + 1;
|
|
}
|
|
|
|
// An anchor point is found. Save the {target, count} pair
|
|
TargetCountMap[Target] = count;
|
|
if (n4 == Rest.size())
|
|
break;
|
|
// Change n3 to the next blank space after colon + integer pair.
|
|
n3 = n4;
|
|
}
|
|
} else {
|
|
LineTy = LineType::CallSiteProfile;
|
|
size_t n3 = Rest.find_last_of(':');
|
|
CalleeName = Rest.substr(0, n3);
|
|
if (Rest.substr(n3 + 1).getAsInteger(10, NumSamples))
|
|
return false;
|
|
}
|
|
return true;
|
|
}
|
|
|
|
/// Load samples from a text file.
|
|
///
|
|
/// See the documentation at the top of the file for an explanation of
|
|
/// the expected format.
|
|
///
|
|
/// \returns true if the file was loaded successfully, false otherwise.
|
|
std::error_code SampleProfileReaderText::readImpl() {
|
|
line_iterator LineIt(*Buffer, /*SkipBlanks=*/true, '#');
|
|
sampleprof_error Result = sampleprof_error::success;
|
|
|
|
InlineCallStack InlineStack;
|
|
uint32_t ProbeProfileCount = 0;
|
|
|
|
// SeenMetadata tracks whether we have processed metadata for the current
|
|
// top-level function profile.
|
|
bool SeenMetadata = false;
|
|
|
|
for (; !LineIt.is_at_eof(); ++LineIt) {
|
|
if ((*LineIt)[(*LineIt).find_first_not_of(' ')] == '#')
|
|
continue;
|
|
// Read the header of each function.
|
|
//
|
|
// Note that for function identifiers we are actually expecting
|
|
// mangled names, but we may not always get them. This happens when
|
|
// the compiler decides not to emit the function (e.g., it was inlined
|
|
// and removed). In this case, the binary will not have the linkage
|
|
// name for the function, so the profiler will emit the function's
|
|
// unmangled name, which may contain characters like ':' and '>' in its
|
|
// name (member functions, templates, etc).
|
|
//
|
|
// The only requirement we place on the identifier, then, is that it
|
|
// should not begin with a number.
|
|
if ((*LineIt)[0] != ' ') {
|
|
uint64_t NumSamples, NumHeadSamples;
|
|
StringRef FName;
|
|
if (!ParseHead(*LineIt, FName, NumSamples, NumHeadSamples)) {
|
|
reportError(LineIt.line_number(),
|
|
"Expected 'mangled_name:NUM:NUM', found " + *LineIt);
|
|
return sampleprof_error::malformed;
|
|
}
|
|
SeenMetadata = false;
|
|
SampleContext FContext(FName);
|
|
if (FContext.hasContext())
|
|
++CSProfileCount;
|
|
Profiles[FContext] = FunctionSamples();
|
|
FunctionSamples &FProfile = Profiles[FContext];
|
|
FProfile.setName(FContext.getNameWithoutContext());
|
|
FProfile.setContext(FContext);
|
|
MergeResult(Result, FProfile.addTotalSamples(NumSamples));
|
|
MergeResult(Result, FProfile.addHeadSamples(NumHeadSamples));
|
|
InlineStack.clear();
|
|
InlineStack.push_back(&FProfile);
|
|
} else {
|
|
uint64_t NumSamples;
|
|
StringRef FName;
|
|
DenseMap<StringRef, uint64_t> TargetCountMap;
|
|
uint32_t Depth, LineOffset, Discriminator;
|
|
LineType LineTy;
|
|
uint64_t FunctionHash = 0;
|
|
uint32_t Attributes = 0;
|
|
if (!ParseLine(*LineIt, LineTy, Depth, NumSamples, LineOffset,
|
|
Discriminator, FName, TargetCountMap, FunctionHash,
|
|
Attributes)) {
|
|
reportError(LineIt.line_number(),
|
|
"Expected 'NUM[.NUM]: NUM[ mangled_name:NUM]*', found " +
|
|
*LineIt);
|
|
return sampleprof_error::malformed;
|
|
}
|
|
if (SeenMetadata && LineTy != LineType::Metadata) {
|
|
// Metadata must be put at the end of a function profile.
|
|
reportError(LineIt.line_number(),
|
|
"Found non-metadata after metadata: " + *LineIt);
|
|
return sampleprof_error::malformed;
|
|
}
|
|
while (InlineStack.size() > Depth) {
|
|
InlineStack.pop_back();
|
|
}
|
|
switch (LineTy) {
|
|
case LineType::CallSiteProfile: {
|
|
FunctionSamples &FSamples = InlineStack.back()->functionSamplesAt(
|
|
LineLocation(LineOffset, Discriminator))[std::string(FName)];
|
|
FSamples.setName(FName);
|
|
MergeResult(Result, FSamples.addTotalSamples(NumSamples));
|
|
InlineStack.push_back(&FSamples);
|
|
break;
|
|
}
|
|
case LineType::BodyProfile: {
|
|
while (InlineStack.size() > Depth) {
|
|
InlineStack.pop_back();
|
|
}
|
|
FunctionSamples &FProfile = *InlineStack.back();
|
|
for (const auto &name_count : TargetCountMap) {
|
|
MergeResult(Result, FProfile.addCalledTargetSamples(
|
|
LineOffset, Discriminator, name_count.first,
|
|
name_count.second));
|
|
}
|
|
MergeResult(Result, FProfile.addBodySamples(LineOffset, Discriminator,
|
|
NumSamples));
|
|
break;
|
|
}
|
|
case LineType::Metadata: {
|
|
FunctionSamples &FProfile = *InlineStack.back();
|
|
if (FunctionHash) {
|
|
FProfile.setFunctionHash(FunctionHash);
|
|
++ProbeProfileCount;
|
|
}
|
|
if (Attributes)
|
|
FProfile.getContext().setAllAttributes(Attributes);
|
|
SeenMetadata = true;
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
assert((CSProfileCount == 0 || CSProfileCount == Profiles.size()) &&
|
|
"Cannot have both context-sensitive and regular profile");
|
|
ProfileIsCS = (CSProfileCount > 0);
|
|
assert((ProbeProfileCount == 0 || ProbeProfileCount == Profiles.size()) &&
|
|
"Cannot have both probe-based profiles and regular profiles");
|
|
ProfileIsProbeBased = (ProbeProfileCount > 0);
|
|
FunctionSamples::ProfileIsProbeBased = ProfileIsProbeBased;
|
|
FunctionSamples::ProfileIsCS = ProfileIsCS;
|
|
|
|
if (Result == sampleprof_error::success)
|
|
computeSummary();
|
|
|
|
return Result;
|
|
}
|
|
|
|
bool SampleProfileReaderText::hasFormat(const MemoryBuffer &Buffer) {
|
|
bool result = false;
|
|
|
|
// Check that the first non-comment line is a valid function header.
|
|
line_iterator LineIt(Buffer, /*SkipBlanks=*/true, '#');
|
|
if (!LineIt.is_at_eof()) {
|
|
if ((*LineIt)[0] != ' ') {
|
|
uint64_t NumSamples, NumHeadSamples;
|
|
StringRef FName;
|
|
result = ParseHead(*LineIt, FName, NumSamples, NumHeadSamples);
|
|
}
|
|
}
|
|
|
|
return result;
|
|
}
|
|
|
|
template <typename T> ErrorOr<T> SampleProfileReaderBinary::readNumber() {
|
|
unsigned NumBytesRead = 0;
|
|
std::error_code EC;
|
|
uint64_t Val = decodeULEB128(Data, &NumBytesRead);
|
|
|
|
if (Val > std::numeric_limits<T>::max())
|
|
EC = sampleprof_error::malformed;
|
|
else if (Data + NumBytesRead > End)
|
|
EC = sampleprof_error::truncated;
|
|
else
|
|
EC = sampleprof_error::success;
|
|
|
|
if (EC) {
|
|
reportError(0, EC.message());
|
|
return EC;
|
|
}
|
|
|
|
Data += NumBytesRead;
|
|
return static_cast<T>(Val);
|
|
}
|
|
|
|
ErrorOr<StringRef> SampleProfileReaderBinary::readString() {
|
|
std::error_code EC;
|
|
StringRef Str(reinterpret_cast<const char *>(Data));
|
|
if (Data + Str.size() + 1 > End) {
|
|
EC = sampleprof_error::truncated;
|
|
reportError(0, EC.message());
|
|
return EC;
|
|
}
|
|
|
|
Data += Str.size() + 1;
|
|
return Str;
|
|
}
|
|
|
|
template <typename T>
|
|
ErrorOr<T> SampleProfileReaderBinary::readUnencodedNumber() {
|
|
std::error_code EC;
|
|
|
|
if (Data + sizeof(T) > End) {
|
|
EC = sampleprof_error::truncated;
|
|
reportError(0, EC.message());
|
|
return EC;
|
|
}
|
|
|
|
using namespace support;
|
|
T Val = endian::readNext<T, little, unaligned>(Data);
|
|
return Val;
|
|
}
|
|
|
|
template <typename T>
|
|
inline ErrorOr<uint32_t> SampleProfileReaderBinary::readStringIndex(T &Table) {
|
|
std::error_code EC;
|
|
auto Idx = readNumber<uint32_t>();
|
|
if (std::error_code EC = Idx.getError())
|
|
return EC;
|
|
if (*Idx >= Table.size())
|
|
return sampleprof_error::truncated_name_table;
|
|
return *Idx;
|
|
}
|
|
|
|
ErrorOr<StringRef> SampleProfileReaderBinary::readStringFromTable() {
|
|
auto Idx = readStringIndex(NameTable);
|
|
if (std::error_code EC = Idx.getError())
|
|
return EC;
|
|
|
|
return NameTable[*Idx];
|
|
}
|
|
|
|
ErrorOr<StringRef> SampleProfileReaderExtBinaryBase::readStringFromTable() {
|
|
if (!FixedLengthMD5)
|
|
return SampleProfileReaderBinary::readStringFromTable();
|
|
|
|
// read NameTable index.
|
|
auto Idx = readStringIndex(NameTable);
|
|
if (std::error_code EC = Idx.getError())
|
|
return EC;
|
|
|
|
// Check whether the name to be accessed has been accessed before,
|
|
// if not, read it from memory directly.
|
|
StringRef &SR = NameTable[*Idx];
|
|
if (SR.empty()) {
|
|
const uint8_t *SavedData = Data;
|
|
Data = MD5NameMemStart + ((*Idx) * sizeof(uint64_t));
|
|
auto FID = readUnencodedNumber<uint64_t>();
|
|
if (std::error_code EC = FID.getError())
|
|
return EC;
|
|
// Save the string converted from uint64_t in MD5StringBuf. All the
|
|
// references to the name are all StringRefs refering to the string
|
|
// in MD5StringBuf.
|
|
MD5StringBuf->push_back(std::to_string(*FID));
|
|
SR = MD5StringBuf->back();
|
|
Data = SavedData;
|
|
}
|
|
return SR;
|
|
}
|
|
|
|
ErrorOr<StringRef> SampleProfileReaderCompactBinary::readStringFromTable() {
|
|
auto Idx = readStringIndex(NameTable);
|
|
if (std::error_code EC = Idx.getError())
|
|
return EC;
|
|
|
|
return StringRef(NameTable[*Idx]);
|
|
}
|
|
|
|
std::error_code
|
|
SampleProfileReaderBinary::readProfile(FunctionSamples &FProfile) {
|
|
auto NumSamples = readNumber<uint64_t>();
|
|
if (std::error_code EC = NumSamples.getError())
|
|
return EC;
|
|
FProfile.addTotalSamples(*NumSamples);
|
|
|
|
// Read the samples in the body.
|
|
auto NumRecords = readNumber<uint32_t>();
|
|
if (std::error_code EC = NumRecords.getError())
|
|
return EC;
|
|
|
|
for (uint32_t I = 0; I < *NumRecords; ++I) {
|
|
auto LineOffset = readNumber<uint64_t>();
|
|
if (std::error_code EC = LineOffset.getError())
|
|
return EC;
|
|
|
|
if (!isOffsetLegal(*LineOffset)) {
|
|
return std::error_code();
|
|
}
|
|
|
|
auto Discriminator = readNumber<uint64_t>();
|
|
if (std::error_code EC = Discriminator.getError())
|
|
return EC;
|
|
|
|
auto NumSamples = readNumber<uint64_t>();
|
|
if (std::error_code EC = NumSamples.getError())
|
|
return EC;
|
|
|
|
auto NumCalls = readNumber<uint32_t>();
|
|
if (std::error_code EC = NumCalls.getError())
|
|
return EC;
|
|
|
|
for (uint32_t J = 0; J < *NumCalls; ++J) {
|
|
auto CalledFunction(readStringFromTable());
|
|
if (std::error_code EC = CalledFunction.getError())
|
|
return EC;
|
|
|
|
auto CalledFunctionSamples = readNumber<uint64_t>();
|
|
if (std::error_code EC = CalledFunctionSamples.getError())
|
|
return EC;
|
|
|
|
FProfile.addCalledTargetSamples(*LineOffset, *Discriminator,
|
|
*CalledFunction, *CalledFunctionSamples);
|
|
}
|
|
|
|
FProfile.addBodySamples(*LineOffset, *Discriminator, *NumSamples);
|
|
}
|
|
|
|
// Read all the samples for inlined function calls.
|
|
auto NumCallsites = readNumber<uint32_t>();
|
|
if (std::error_code EC = NumCallsites.getError())
|
|
return EC;
|
|
|
|
for (uint32_t J = 0; J < *NumCallsites; ++J) {
|
|
auto LineOffset = readNumber<uint64_t>();
|
|
if (std::error_code EC = LineOffset.getError())
|
|
return EC;
|
|
|
|
auto Discriminator = readNumber<uint64_t>();
|
|
if (std::error_code EC = Discriminator.getError())
|
|
return EC;
|
|
|
|
auto FName(readStringFromTable());
|
|
if (std::error_code EC = FName.getError())
|
|
return EC;
|
|
|
|
FunctionSamples &CalleeProfile = FProfile.functionSamplesAt(
|
|
LineLocation(*LineOffset, *Discriminator))[std::string(*FName)];
|
|
CalleeProfile.setName(*FName);
|
|
if (std::error_code EC = readProfile(CalleeProfile))
|
|
return EC;
|
|
}
|
|
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code
|
|
SampleProfileReaderBinary::readFuncProfile(const uint8_t *Start) {
|
|
Data = Start;
|
|
auto NumHeadSamples = readNumber<uint64_t>();
|
|
if (std::error_code EC = NumHeadSamples.getError())
|
|
return EC;
|
|
|
|
auto FName(readStringFromTable());
|
|
if (std::error_code EC = FName.getError())
|
|
return EC;
|
|
|
|
SampleContext FContext(*FName);
|
|
Profiles[FContext] = FunctionSamples();
|
|
FunctionSamples &FProfile = Profiles[FContext];
|
|
FProfile.setName(FContext.getNameWithoutContext());
|
|
FProfile.setContext(FContext);
|
|
FProfile.addHeadSamples(*NumHeadSamples);
|
|
|
|
if (FContext.hasContext())
|
|
CSProfileCount++;
|
|
|
|
if (std::error_code EC = readProfile(FProfile))
|
|
return EC;
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderBinary::readImpl() {
|
|
while (!at_eof()) {
|
|
if (std::error_code EC = readFuncProfile(Data))
|
|
return EC;
|
|
}
|
|
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderExtBinaryBase::readOneSection(
|
|
const uint8_t *Start, uint64_t Size, const SecHdrTableEntry &Entry) {
|
|
Data = Start;
|
|
End = Start + Size;
|
|
switch (Entry.Type) {
|
|
case SecProfSummary:
|
|
if (std::error_code EC = readSummary())
|
|
return EC;
|
|
if (hasSecFlag(Entry, SecProfSummaryFlags::SecFlagPartial))
|
|
Summary->setPartialProfile(true);
|
|
if (hasSecFlag(Entry, SecProfSummaryFlags::SecFlagFullContext))
|
|
FunctionSamples::ProfileIsCS = ProfileIsCS = true;
|
|
break;
|
|
case SecNameTable: {
|
|
FixedLengthMD5 =
|
|
hasSecFlag(Entry, SecNameTableFlags::SecFlagFixedLengthMD5);
|
|
bool UseMD5 = hasSecFlag(Entry, SecNameTableFlags::SecFlagMD5Name);
|
|
assert((!FixedLengthMD5 || UseMD5) &&
|
|
"If FixedLengthMD5 is true, UseMD5 has to be true");
|
|
FunctionSamples::HasUniqSuffix =
|
|
hasSecFlag(Entry, SecNameTableFlags::SecFlagUniqSuffix);
|
|
if (std::error_code EC = readNameTableSec(UseMD5))
|
|
return EC;
|
|
break;
|
|
}
|
|
case SecLBRProfile:
|
|
if (std::error_code EC = readFuncProfiles())
|
|
return EC;
|
|
break;
|
|
case SecFuncOffsetTable:
|
|
if (std::error_code EC = readFuncOffsetTable())
|
|
return EC;
|
|
break;
|
|
case SecFuncMetadata: {
|
|
ProfileIsProbeBased =
|
|
hasSecFlag(Entry, SecFuncMetadataFlags::SecFlagIsProbeBased);
|
|
FunctionSamples::ProfileIsProbeBased = ProfileIsProbeBased;
|
|
bool HasAttribute =
|
|
hasSecFlag(Entry, SecFuncMetadataFlags::SecFlagHasAttribute);
|
|
if (std::error_code EC = readFuncMetadata(HasAttribute))
|
|
return EC;
|
|
break;
|
|
}
|
|
case SecProfileSymbolList:
|
|
if (std::error_code EC = readProfileSymbolList())
|
|
return EC;
|
|
break;
|
|
default:
|
|
if (std::error_code EC = readCustomSection(Entry))
|
|
return EC;
|
|
break;
|
|
}
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
bool SampleProfileReaderExtBinaryBase::collectFuncsFromModule() {
|
|
if (!M)
|
|
return false;
|
|
FuncsToUse.clear();
|
|
for (auto &F : *M)
|
|
FuncsToUse.insert(FunctionSamples::getCanonicalFnName(F));
|
|
return true;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderExtBinaryBase::readFuncOffsetTable() {
|
|
// If there are more than one FuncOffsetTable, the profile read associated
|
|
// with previous FuncOffsetTable has to be done before next FuncOffsetTable
|
|
// is read.
|
|
FuncOffsetTable.clear();
|
|
|
|
auto Size = readNumber<uint64_t>();
|
|
if (std::error_code EC = Size.getError())
|
|
return EC;
|
|
|
|
FuncOffsetTable.reserve(*Size);
|
|
for (uint32_t I = 0; I < *Size; ++I) {
|
|
auto FName(readStringFromTable());
|
|
if (std::error_code EC = FName.getError())
|
|
return EC;
|
|
|
|
auto Offset = readNumber<uint64_t>();
|
|
if (std::error_code EC = Offset.getError())
|
|
return EC;
|
|
|
|
FuncOffsetTable[*FName] = *Offset;
|
|
}
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderExtBinaryBase::readFuncProfiles() {
|
|
// Collect functions used by current module if the Reader has been
|
|
// given a module.
|
|
// collectFuncsFromModule uses FunctionSamples::getCanonicalFnName
|
|
// which will query FunctionSamples::HasUniqSuffix, so it has to be
|
|
// called after FunctionSamples::HasUniqSuffix is set, i.e. after
|
|
// NameTable section is read.
|
|
bool LoadFuncsToBeUsed = collectFuncsFromModule();
|
|
|
|
// When LoadFuncsToBeUsed is false, load all the function profiles.
|
|
const uint8_t *Start = Data;
|
|
if (!LoadFuncsToBeUsed) {
|
|
while (Data < End) {
|
|
if (std::error_code EC = readFuncProfile(Data))
|
|
return EC;
|
|
}
|
|
assert(Data == End && "More data is read than expected");
|
|
} else {
|
|
// Load function profiles on demand.
|
|
if (Remapper) {
|
|
for (auto Name : FuncsToUse) {
|
|
Remapper->insert(Name);
|
|
}
|
|
}
|
|
|
|
if (useMD5()) {
|
|
for (auto Name : FuncsToUse) {
|
|
auto GUID = std::to_string(MD5Hash(Name));
|
|
auto iter = FuncOffsetTable.find(StringRef(GUID));
|
|
if (iter == FuncOffsetTable.end())
|
|
continue;
|
|
const uint8_t *FuncProfileAddr = Start + iter->second;
|
|
assert(FuncProfileAddr < End && "out of LBRProfile section");
|
|
if (std::error_code EC = readFuncProfile(FuncProfileAddr))
|
|
return EC;
|
|
}
|
|
} else if (FunctionSamples::ProfileIsCS) {
|
|
// Compute the ordered set of names, so we can
|
|
// get all context profiles under a subtree by
|
|
// iterating through the ordered names.
|
|
struct Comparer {
|
|
// Ignore the closing ']' when ordering context
|
|
bool operator()(const StringRef &L, const StringRef &R) const {
|
|
return L.substr(0, L.size() - 1) < R.substr(0, R.size() - 1);
|
|
}
|
|
};
|
|
std::set<StringRef, Comparer> OrderedNames;
|
|
for (auto Name : FuncOffsetTable) {
|
|
OrderedNames.insert(Name.first);
|
|
}
|
|
|
|
// For each function in current module, load all
|
|
// context profiles for the function.
|
|
for (auto NameOffset : FuncOffsetTable) {
|
|
StringRef ContextName = NameOffset.first;
|
|
SampleContext FContext(ContextName);
|
|
auto FuncName = FContext.getNameWithoutContext();
|
|
if (!FuncsToUse.count(FuncName) &&
|
|
(!Remapper || !Remapper->exist(FuncName)))
|
|
continue;
|
|
|
|
// For each context profile we need, try to load
|
|
// all context profile in the subtree. This can
|
|
// help profile guided importing for ThinLTO.
|
|
auto It = OrderedNames.find(ContextName);
|
|
while (It != OrderedNames.end() &&
|
|
It->startswith(ContextName.substr(0, ContextName.size() - 1))) {
|
|
const uint8_t *FuncProfileAddr = Start + FuncOffsetTable[*It];
|
|
assert(FuncProfileAddr < End && "out of LBRProfile section");
|
|
if (std::error_code EC = readFuncProfile(FuncProfileAddr))
|
|
return EC;
|
|
// Remove loaded context profile so we won't
|
|
// load it repeatedly.
|
|
It = OrderedNames.erase(It);
|
|
}
|
|
}
|
|
} else {
|
|
for (auto NameOffset : FuncOffsetTable) {
|
|
SampleContext FContext(NameOffset.first);
|
|
auto FuncName = FContext.getNameWithoutContext();
|
|
if (!FuncsToUse.count(FuncName) &&
|
|
(!Remapper || !Remapper->exist(FuncName)))
|
|
continue;
|
|
const uint8_t *FuncProfileAddr = Start + NameOffset.second;
|
|
assert(FuncProfileAddr < End && "out of LBRProfile section");
|
|
if (std::error_code EC = readFuncProfile(FuncProfileAddr))
|
|
return EC;
|
|
}
|
|
}
|
|
Data = End;
|
|
}
|
|
assert((CSProfileCount == 0 || CSProfileCount == Profiles.size()) &&
|
|
"Cannot have both context-sensitive and regular profile");
|
|
assert(ProfileIsCS == (CSProfileCount > 0) &&
|
|
"Section flag should be consistent with actual profile");
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderExtBinaryBase::readProfileSymbolList() {
|
|
if (!ProfSymList)
|
|
ProfSymList = std::make_unique<ProfileSymbolList>();
|
|
|
|
if (std::error_code EC = ProfSymList->read(Data, End - Data))
|
|
return EC;
|
|
|
|
Data = End;
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderExtBinaryBase::decompressSection(
|
|
const uint8_t *SecStart, const uint64_t SecSize,
|
|
const uint8_t *&DecompressBuf, uint64_t &DecompressBufSize) {
|
|
Data = SecStart;
|
|
End = SecStart + SecSize;
|
|
auto DecompressSize = readNumber<uint64_t>();
|
|
if (std::error_code EC = DecompressSize.getError())
|
|
return EC;
|
|
DecompressBufSize = *DecompressSize;
|
|
|
|
auto CompressSize = readNumber<uint64_t>();
|
|
if (std::error_code EC = CompressSize.getError())
|
|
return EC;
|
|
|
|
if (!llvm::zlib::isAvailable())
|
|
return sampleprof_error::zlib_unavailable;
|
|
|
|
StringRef CompressedStrings(reinterpret_cast<const char *>(Data),
|
|
*CompressSize);
|
|
char *Buffer = Allocator.Allocate<char>(DecompressBufSize);
|
|
size_t UCSize = DecompressBufSize;
|
|
llvm::Error E =
|
|
zlib::uncompress(CompressedStrings, Buffer, UCSize);
|
|
if (E)
|
|
return sampleprof_error::uncompress_failed;
|
|
DecompressBuf = reinterpret_cast<const uint8_t *>(Buffer);
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderExtBinaryBase::readImpl() {
|
|
const uint8_t *BufStart =
|
|
reinterpret_cast<const uint8_t *>(Buffer->getBufferStart());
|
|
|
|
for (auto &Entry : SecHdrTable) {
|
|
// Skip empty section.
|
|
if (!Entry.Size)
|
|
continue;
|
|
|
|
// Skip sections without context when SkipFlatProf is true.
|
|
if (SkipFlatProf && hasSecFlag(Entry, SecCommonFlags::SecFlagFlat))
|
|
continue;
|
|
|
|
const uint8_t *SecStart = BufStart + Entry.Offset;
|
|
uint64_t SecSize = Entry.Size;
|
|
|
|
// If the section is compressed, decompress it into a buffer
|
|
// DecompressBuf before reading the actual data. The pointee of
|
|
// 'Data' will be changed to buffer hold by DecompressBuf
|
|
// temporarily when reading the actual data.
|
|
bool isCompressed = hasSecFlag(Entry, SecCommonFlags::SecFlagCompress);
|
|
if (isCompressed) {
|
|
const uint8_t *DecompressBuf;
|
|
uint64_t DecompressBufSize;
|
|
if (std::error_code EC = decompressSection(
|
|
SecStart, SecSize, DecompressBuf, DecompressBufSize))
|
|
return EC;
|
|
SecStart = DecompressBuf;
|
|
SecSize = DecompressBufSize;
|
|
}
|
|
|
|
if (std::error_code EC = readOneSection(SecStart, SecSize, Entry))
|
|
return EC;
|
|
if (Data != SecStart + SecSize)
|
|
return sampleprof_error::malformed;
|
|
|
|
// Change the pointee of 'Data' from DecompressBuf to original Buffer.
|
|
if (isCompressed) {
|
|
Data = BufStart + Entry.Offset;
|
|
End = BufStart + Buffer->getBufferSize();
|
|
}
|
|
}
|
|
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderCompactBinary::readImpl() {
|
|
// Collect functions used by current module if the Reader has been
|
|
// given a module.
|
|
bool LoadFuncsToBeUsed = collectFuncsFromModule();
|
|
|
|
std::vector<uint64_t> OffsetsToUse;
|
|
if (!LoadFuncsToBeUsed) {
|
|
// load all the function profiles.
|
|
for (auto FuncEntry : FuncOffsetTable) {
|
|
OffsetsToUse.push_back(FuncEntry.second);
|
|
}
|
|
} else {
|
|
// load function profiles on demand.
|
|
for (auto Name : FuncsToUse) {
|
|
auto GUID = std::to_string(MD5Hash(Name));
|
|
auto iter = FuncOffsetTable.find(StringRef(GUID));
|
|
if (iter == FuncOffsetTable.end())
|
|
continue;
|
|
OffsetsToUse.push_back(iter->second);
|
|
}
|
|
}
|
|
|
|
for (auto Offset : OffsetsToUse) {
|
|
const uint8_t *SavedData = Data;
|
|
if (std::error_code EC = readFuncProfile(
|
|
reinterpret_cast<const uint8_t *>(Buffer->getBufferStart()) +
|
|
Offset))
|
|
return EC;
|
|
Data = SavedData;
|
|
}
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderRawBinary::verifySPMagic(uint64_t Magic) {
|
|
if (Magic == SPMagic())
|
|
return sampleprof_error::success;
|
|
return sampleprof_error::bad_magic;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderExtBinary::verifySPMagic(uint64_t Magic) {
|
|
if (Magic == SPMagic(SPF_Ext_Binary))
|
|
return sampleprof_error::success;
|
|
return sampleprof_error::bad_magic;
|
|
}
|
|
|
|
std::error_code
|
|
SampleProfileReaderCompactBinary::verifySPMagic(uint64_t Magic) {
|
|
if (Magic == SPMagic(SPF_Compact_Binary))
|
|
return sampleprof_error::success;
|
|
return sampleprof_error::bad_magic;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderBinary::readNameTable() {
|
|
auto Size = readNumber<uint32_t>();
|
|
if (std::error_code EC = Size.getError())
|
|
return EC;
|
|
NameTable.reserve(*Size + NameTable.size());
|
|
for (uint32_t I = 0; I < *Size; ++I) {
|
|
auto Name(readString());
|
|
if (std::error_code EC = Name.getError())
|
|
return EC;
|
|
NameTable.push_back(*Name);
|
|
}
|
|
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderExtBinaryBase::readMD5NameTable() {
|
|
auto Size = readNumber<uint64_t>();
|
|
if (std::error_code EC = Size.getError())
|
|
return EC;
|
|
MD5StringBuf = std::make_unique<std::vector<std::string>>();
|
|
MD5StringBuf->reserve(*Size);
|
|
if (FixedLengthMD5) {
|
|
// Preallocate and initialize NameTable so we can check whether a name
|
|
// index has been read before by checking whether the element in the
|
|
// NameTable is empty, meanwhile readStringIndex can do the boundary
|
|
// check using the size of NameTable.
|
|
NameTable.resize(*Size + NameTable.size());
|
|
|
|
MD5NameMemStart = Data;
|
|
Data = Data + (*Size) * sizeof(uint64_t);
|
|
return sampleprof_error::success;
|
|
}
|
|
NameTable.reserve(*Size);
|
|
for (uint32_t I = 0; I < *Size; ++I) {
|
|
auto FID = readNumber<uint64_t>();
|
|
if (std::error_code EC = FID.getError())
|
|
return EC;
|
|
MD5StringBuf->push_back(std::to_string(*FID));
|
|
// NameTable is a vector of StringRef. Here it is pushing back a
|
|
// StringRef initialized with the last string in MD5stringBuf.
|
|
NameTable.push_back(MD5StringBuf->back());
|
|
}
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderExtBinaryBase::readNameTableSec(bool IsMD5) {
|
|
if (IsMD5)
|
|
return readMD5NameTable();
|
|
return SampleProfileReaderBinary::readNameTable();
|
|
}
|
|
|
|
std::error_code
|
|
SampleProfileReaderExtBinaryBase::readFuncMetadata(bool ProfileHasAttribute) {
|
|
while (Data < End) {
|
|
auto FName(readStringFromTable());
|
|
if (std::error_code EC = FName.getError())
|
|
return EC;
|
|
|
|
SampleContext FContext(*FName);
|
|
bool ProfileInMap = Profiles.count(FContext);
|
|
|
|
if (ProfileIsProbeBased) {
|
|
auto Checksum = readNumber<uint64_t>();
|
|
if (std::error_code EC = Checksum.getError())
|
|
return EC;
|
|
if (ProfileInMap)
|
|
Profiles[FContext].setFunctionHash(*Checksum);
|
|
}
|
|
|
|
if (ProfileHasAttribute) {
|
|
auto Attributes = readNumber<uint32_t>();
|
|
if (std::error_code EC = Attributes.getError())
|
|
return EC;
|
|
if (ProfileInMap)
|
|
Profiles[FContext].getContext().setAllAttributes(*Attributes);
|
|
}
|
|
}
|
|
|
|
assert(Data == End && "More data is read than expected");
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderCompactBinary::readNameTable() {
|
|
auto Size = readNumber<uint64_t>();
|
|
if (std::error_code EC = Size.getError())
|
|
return EC;
|
|
NameTable.reserve(*Size);
|
|
for (uint32_t I = 0; I < *Size; ++I) {
|
|
auto FID = readNumber<uint64_t>();
|
|
if (std::error_code EC = FID.getError())
|
|
return EC;
|
|
NameTable.push_back(std::to_string(*FID));
|
|
}
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code
|
|
SampleProfileReaderExtBinaryBase::readSecHdrTableEntry(uint32_t Idx) {
|
|
SecHdrTableEntry Entry;
|
|
auto Type = readUnencodedNumber<uint64_t>();
|
|
if (std::error_code EC = Type.getError())
|
|
return EC;
|
|
Entry.Type = static_cast<SecType>(*Type);
|
|
|
|
auto Flags = readUnencodedNumber<uint64_t>();
|
|
if (std::error_code EC = Flags.getError())
|
|
return EC;
|
|
Entry.Flags = *Flags;
|
|
|
|
auto Offset = readUnencodedNumber<uint64_t>();
|
|
if (std::error_code EC = Offset.getError())
|
|
return EC;
|
|
Entry.Offset = *Offset;
|
|
|
|
auto Size = readUnencodedNumber<uint64_t>();
|
|
if (std::error_code EC = Size.getError())
|
|
return EC;
|
|
Entry.Size = *Size;
|
|
|
|
Entry.LayoutIndex = Idx;
|
|
SecHdrTable.push_back(std::move(Entry));
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderExtBinaryBase::readSecHdrTable() {
|
|
auto EntryNum = readUnencodedNumber<uint64_t>();
|
|
if (std::error_code EC = EntryNum.getError())
|
|
return EC;
|
|
|
|
for (uint32_t i = 0; i < (*EntryNum); i++)
|
|
if (std::error_code EC = readSecHdrTableEntry(i))
|
|
return EC;
|
|
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderExtBinaryBase::readHeader() {
|
|
const uint8_t *BufStart =
|
|
reinterpret_cast<const uint8_t *>(Buffer->getBufferStart());
|
|
Data = BufStart;
|
|
End = BufStart + Buffer->getBufferSize();
|
|
|
|
if (std::error_code EC = readMagicIdent())
|
|
return EC;
|
|
|
|
if (std::error_code EC = readSecHdrTable())
|
|
return EC;
|
|
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
uint64_t SampleProfileReaderExtBinaryBase::getSectionSize(SecType Type) {
|
|
uint64_t Size = 0;
|
|
for (auto &Entry : SecHdrTable) {
|
|
if (Entry.Type == Type)
|
|
Size += Entry.Size;
|
|
}
|
|
return Size;
|
|
}
|
|
|
|
uint64_t SampleProfileReaderExtBinaryBase::getFileSize() {
|
|
// Sections in SecHdrTable is not necessarily in the same order as
|
|
// sections in the profile because section like FuncOffsetTable needs
|
|
// to be written after section LBRProfile but needs to be read before
|
|
// section LBRProfile, so we cannot simply use the last entry in
|
|
// SecHdrTable to calculate the file size.
|
|
uint64_t FileSize = 0;
|
|
for (auto &Entry : SecHdrTable) {
|
|
FileSize = std::max(Entry.Offset + Entry.Size, FileSize);
|
|
}
|
|
return FileSize;
|
|
}
|
|
|
|
static std::string getSecFlagsStr(const SecHdrTableEntry &Entry) {
|
|
std::string Flags;
|
|
if (hasSecFlag(Entry, SecCommonFlags::SecFlagCompress))
|
|
Flags.append("{compressed,");
|
|
else
|
|
Flags.append("{");
|
|
|
|
if (hasSecFlag(Entry, SecCommonFlags::SecFlagFlat))
|
|
Flags.append("flat,");
|
|
|
|
switch (Entry.Type) {
|
|
case SecNameTable:
|
|
if (hasSecFlag(Entry, SecNameTableFlags::SecFlagFixedLengthMD5))
|
|
Flags.append("fixlenmd5,");
|
|
else if (hasSecFlag(Entry, SecNameTableFlags::SecFlagMD5Name))
|
|
Flags.append("md5,");
|
|
if (hasSecFlag(Entry, SecNameTableFlags::SecFlagUniqSuffix))
|
|
Flags.append("uniq,");
|
|
break;
|
|
case SecProfSummary:
|
|
if (hasSecFlag(Entry, SecProfSummaryFlags::SecFlagPartial))
|
|
Flags.append("partial,");
|
|
if (hasSecFlag(Entry, SecProfSummaryFlags::SecFlagFullContext))
|
|
Flags.append("context,");
|
|
break;
|
|
default:
|
|
break;
|
|
}
|
|
char &last = Flags.back();
|
|
if (last == ',')
|
|
last = '}';
|
|
else
|
|
Flags.append("}");
|
|
return Flags;
|
|
}
|
|
|
|
bool SampleProfileReaderExtBinaryBase::dumpSectionInfo(raw_ostream &OS) {
|
|
uint64_t TotalSecsSize = 0;
|
|
for (auto &Entry : SecHdrTable) {
|
|
OS << getSecName(Entry.Type) << " - Offset: " << Entry.Offset
|
|
<< ", Size: " << Entry.Size << ", Flags: " << getSecFlagsStr(Entry)
|
|
<< "\n";
|
|
;
|
|
TotalSecsSize += Entry.Size;
|
|
}
|
|
uint64_t HeaderSize = SecHdrTable.front().Offset;
|
|
assert(HeaderSize + TotalSecsSize == getFileSize() &&
|
|
"Size of 'header + sections' doesn't match the total size of profile");
|
|
|
|
OS << "Header Size: " << HeaderSize << "\n";
|
|
OS << "Total Sections Size: " << TotalSecsSize << "\n";
|
|
OS << "File Size: " << getFileSize() << "\n";
|
|
return true;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderBinary::readMagicIdent() {
|
|
// Read and check the magic identifier.
|
|
auto Magic = readNumber<uint64_t>();
|
|
if (std::error_code EC = Magic.getError())
|
|
return EC;
|
|
else if (std::error_code EC = verifySPMagic(*Magic))
|
|
return EC;
|
|
|
|
// Read the version number.
|
|
auto Version = readNumber<uint64_t>();
|
|
if (std::error_code EC = Version.getError())
|
|
return EC;
|
|
else if (*Version != SPVersion())
|
|
return sampleprof_error::unsupported_version;
|
|
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderBinary::readHeader() {
|
|
Data = reinterpret_cast<const uint8_t *>(Buffer->getBufferStart());
|
|
End = Data + Buffer->getBufferSize();
|
|
|
|
if (std::error_code EC = readMagicIdent())
|
|
return EC;
|
|
|
|
if (std::error_code EC = readSummary())
|
|
return EC;
|
|
|
|
if (std::error_code EC = readNameTable())
|
|
return EC;
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderCompactBinary::readHeader() {
|
|
SampleProfileReaderBinary::readHeader();
|
|
if (std::error_code EC = readFuncOffsetTable())
|
|
return EC;
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderCompactBinary::readFuncOffsetTable() {
|
|
auto TableOffset = readUnencodedNumber<uint64_t>();
|
|
if (std::error_code EC = TableOffset.getError())
|
|
return EC;
|
|
|
|
const uint8_t *SavedData = Data;
|
|
const uint8_t *TableStart =
|
|
reinterpret_cast<const uint8_t *>(Buffer->getBufferStart()) +
|
|
*TableOffset;
|
|
Data = TableStart;
|
|
|
|
auto Size = readNumber<uint64_t>();
|
|
if (std::error_code EC = Size.getError())
|
|
return EC;
|
|
|
|
FuncOffsetTable.reserve(*Size);
|
|
for (uint32_t I = 0; I < *Size; ++I) {
|
|
auto FName(readStringFromTable());
|
|
if (std::error_code EC = FName.getError())
|
|
return EC;
|
|
|
|
auto Offset = readNumber<uint64_t>();
|
|
if (std::error_code EC = Offset.getError())
|
|
return EC;
|
|
|
|
FuncOffsetTable[*FName] = *Offset;
|
|
}
|
|
End = TableStart;
|
|
Data = SavedData;
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
bool SampleProfileReaderCompactBinary::collectFuncsFromModule() {
|
|
if (!M)
|
|
return false;
|
|
FuncsToUse.clear();
|
|
for (auto &F : *M)
|
|
FuncsToUse.insert(FunctionSamples::getCanonicalFnName(F));
|
|
return true;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderBinary::readSummaryEntry(
|
|
std::vector<ProfileSummaryEntry> &Entries) {
|
|
auto Cutoff = readNumber<uint64_t>();
|
|
if (std::error_code EC = Cutoff.getError())
|
|
return EC;
|
|
|
|
auto MinBlockCount = readNumber<uint64_t>();
|
|
if (std::error_code EC = MinBlockCount.getError())
|
|
return EC;
|
|
|
|
auto NumBlocks = readNumber<uint64_t>();
|
|
if (std::error_code EC = NumBlocks.getError())
|
|
return EC;
|
|
|
|
Entries.emplace_back(*Cutoff, *MinBlockCount, *NumBlocks);
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderBinary::readSummary() {
|
|
auto TotalCount = readNumber<uint64_t>();
|
|
if (std::error_code EC = TotalCount.getError())
|
|
return EC;
|
|
|
|
auto MaxBlockCount = readNumber<uint64_t>();
|
|
if (std::error_code EC = MaxBlockCount.getError())
|
|
return EC;
|
|
|
|
auto MaxFunctionCount = readNumber<uint64_t>();
|
|
if (std::error_code EC = MaxFunctionCount.getError())
|
|
return EC;
|
|
|
|
auto NumBlocks = readNumber<uint64_t>();
|
|
if (std::error_code EC = NumBlocks.getError())
|
|
return EC;
|
|
|
|
auto NumFunctions = readNumber<uint64_t>();
|
|
if (std::error_code EC = NumFunctions.getError())
|
|
return EC;
|
|
|
|
auto NumSummaryEntries = readNumber<uint64_t>();
|
|
if (std::error_code EC = NumSummaryEntries.getError())
|
|
return EC;
|
|
|
|
std::vector<ProfileSummaryEntry> Entries;
|
|
for (unsigned i = 0; i < *NumSummaryEntries; i++) {
|
|
std::error_code EC = readSummaryEntry(Entries);
|
|
if (EC != sampleprof_error::success)
|
|
return EC;
|
|
}
|
|
Summary = std::make_unique<ProfileSummary>(
|
|
ProfileSummary::PSK_Sample, Entries, *TotalCount, *MaxBlockCount, 0,
|
|
*MaxFunctionCount, *NumBlocks, *NumFunctions);
|
|
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
bool SampleProfileReaderRawBinary::hasFormat(const MemoryBuffer &Buffer) {
|
|
const uint8_t *Data =
|
|
reinterpret_cast<const uint8_t *>(Buffer.getBufferStart());
|
|
uint64_t Magic = decodeULEB128(Data);
|
|
return Magic == SPMagic();
|
|
}
|
|
|
|
bool SampleProfileReaderExtBinary::hasFormat(const MemoryBuffer &Buffer) {
|
|
const uint8_t *Data =
|
|
reinterpret_cast<const uint8_t *>(Buffer.getBufferStart());
|
|
uint64_t Magic = decodeULEB128(Data);
|
|
return Magic == SPMagic(SPF_Ext_Binary);
|
|
}
|
|
|
|
bool SampleProfileReaderCompactBinary::hasFormat(const MemoryBuffer &Buffer) {
|
|
const uint8_t *Data =
|
|
reinterpret_cast<const uint8_t *>(Buffer.getBufferStart());
|
|
uint64_t Magic = decodeULEB128(Data);
|
|
return Magic == SPMagic(SPF_Compact_Binary);
|
|
}
|
|
|
|
std::error_code SampleProfileReaderGCC::skipNextWord() {
|
|
uint32_t dummy;
|
|
if (!GcovBuffer.readInt(dummy))
|
|
return sampleprof_error::truncated;
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
template <typename T> ErrorOr<T> SampleProfileReaderGCC::readNumber() {
|
|
if (sizeof(T) <= sizeof(uint32_t)) {
|
|
uint32_t Val;
|
|
if (GcovBuffer.readInt(Val) && Val <= std::numeric_limits<T>::max())
|
|
return static_cast<T>(Val);
|
|
} else if (sizeof(T) <= sizeof(uint64_t)) {
|
|
uint64_t Val;
|
|
if (GcovBuffer.readInt64(Val) && Val <= std::numeric_limits<T>::max())
|
|
return static_cast<T>(Val);
|
|
}
|
|
|
|
std::error_code EC = sampleprof_error::malformed;
|
|
reportError(0, EC.message());
|
|
return EC;
|
|
}
|
|
|
|
ErrorOr<StringRef> SampleProfileReaderGCC::readString() {
|
|
StringRef Str;
|
|
if (!GcovBuffer.readString(Str))
|
|
return sampleprof_error::truncated;
|
|
return Str;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderGCC::readHeader() {
|
|
// Read the magic identifier.
|
|
if (!GcovBuffer.readGCDAFormat())
|
|
return sampleprof_error::unrecognized_format;
|
|
|
|
// Read the version number. Note - the GCC reader does not validate this
|
|
// version, but the profile creator generates v704.
|
|
GCOV::GCOVVersion version;
|
|
if (!GcovBuffer.readGCOVVersion(version))
|
|
return sampleprof_error::unrecognized_format;
|
|
|
|
if (version != GCOV::V407)
|
|
return sampleprof_error::unsupported_version;
|
|
|
|
// Skip the empty integer.
|
|
if (std::error_code EC = skipNextWord())
|
|
return EC;
|
|
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderGCC::readSectionTag(uint32_t Expected) {
|
|
uint32_t Tag;
|
|
if (!GcovBuffer.readInt(Tag))
|
|
return sampleprof_error::truncated;
|
|
|
|
if (Tag != Expected)
|
|
return sampleprof_error::malformed;
|
|
|
|
if (std::error_code EC = skipNextWord())
|
|
return EC;
|
|
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderGCC::readNameTable() {
|
|
if (std::error_code EC = readSectionTag(GCOVTagAFDOFileNames))
|
|
return EC;
|
|
|
|
uint32_t Size;
|
|
if (!GcovBuffer.readInt(Size))
|
|
return sampleprof_error::truncated;
|
|
|
|
for (uint32_t I = 0; I < Size; ++I) {
|
|
StringRef Str;
|
|
if (!GcovBuffer.readString(Str))
|
|
return sampleprof_error::truncated;
|
|
Names.push_back(std::string(Str));
|
|
}
|
|
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderGCC::readFunctionProfiles() {
|
|
if (std::error_code EC = readSectionTag(GCOVTagAFDOFunction))
|
|
return EC;
|
|
|
|
uint32_t NumFunctions;
|
|
if (!GcovBuffer.readInt(NumFunctions))
|
|
return sampleprof_error::truncated;
|
|
|
|
InlineCallStack Stack;
|
|
for (uint32_t I = 0; I < NumFunctions; ++I)
|
|
if (std::error_code EC = readOneFunctionProfile(Stack, true, 0))
|
|
return EC;
|
|
|
|
computeSummary();
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
std::error_code SampleProfileReaderGCC::readOneFunctionProfile(
|
|
const InlineCallStack &InlineStack, bool Update, uint32_t Offset) {
|
|
uint64_t HeadCount = 0;
|
|
if (InlineStack.size() == 0)
|
|
if (!GcovBuffer.readInt64(HeadCount))
|
|
return sampleprof_error::truncated;
|
|
|
|
uint32_t NameIdx;
|
|
if (!GcovBuffer.readInt(NameIdx))
|
|
return sampleprof_error::truncated;
|
|
|
|
StringRef Name(Names[NameIdx]);
|
|
|
|
uint32_t NumPosCounts;
|
|
if (!GcovBuffer.readInt(NumPosCounts))
|
|
return sampleprof_error::truncated;
|
|
|
|
uint32_t NumCallsites;
|
|
if (!GcovBuffer.readInt(NumCallsites))
|
|
return sampleprof_error::truncated;
|
|
|
|
FunctionSamples *FProfile = nullptr;
|
|
if (InlineStack.size() == 0) {
|
|
// If this is a top function that we have already processed, do not
|
|
// update its profile again. This happens in the presence of
|
|
// function aliases. Since these aliases share the same function
|
|
// body, there will be identical replicated profiles for the
|
|
// original function. In this case, we simply not bother updating
|
|
// the profile of the original function.
|
|
FProfile = &Profiles[Name];
|
|
FProfile->addHeadSamples(HeadCount);
|
|
if (FProfile->getTotalSamples() > 0)
|
|
Update = false;
|
|
} else {
|
|
// Otherwise, we are reading an inlined instance. The top of the
|
|
// inline stack contains the profile of the caller. Insert this
|
|
// callee in the caller's CallsiteMap.
|
|
FunctionSamples *CallerProfile = InlineStack.front();
|
|
uint32_t LineOffset = Offset >> 16;
|
|
uint32_t Discriminator = Offset & 0xffff;
|
|
FProfile = &CallerProfile->functionSamplesAt(
|
|
LineLocation(LineOffset, Discriminator))[std::string(Name)];
|
|
}
|
|
FProfile->setName(Name);
|
|
|
|
for (uint32_t I = 0; I < NumPosCounts; ++I) {
|
|
uint32_t Offset;
|
|
if (!GcovBuffer.readInt(Offset))
|
|
return sampleprof_error::truncated;
|
|
|
|
uint32_t NumTargets;
|
|
if (!GcovBuffer.readInt(NumTargets))
|
|
return sampleprof_error::truncated;
|
|
|
|
uint64_t Count;
|
|
if (!GcovBuffer.readInt64(Count))
|
|
return sampleprof_error::truncated;
|
|
|
|
// The line location is encoded in the offset as:
|
|
// high 16 bits: line offset to the start of the function.
|
|
// low 16 bits: discriminator.
|
|
uint32_t LineOffset = Offset >> 16;
|
|
uint32_t Discriminator = Offset & 0xffff;
|
|
|
|
InlineCallStack NewStack;
|
|
NewStack.push_back(FProfile);
|
|
llvm::append_range(NewStack, InlineStack);
|
|
if (Update) {
|
|
// Walk up the inline stack, adding the samples on this line to
|
|
// the total sample count of the callers in the chain.
|
|
for (auto CallerProfile : NewStack)
|
|
CallerProfile->addTotalSamples(Count);
|
|
|
|
// Update the body samples for the current profile.
|
|
FProfile->addBodySamples(LineOffset, Discriminator, Count);
|
|
}
|
|
|
|
// Process the list of functions called at an indirect call site.
|
|
// These are all the targets that a function pointer (or virtual
|
|
// function) resolved at runtime.
|
|
for (uint32_t J = 0; J < NumTargets; J++) {
|
|
uint32_t HistVal;
|
|
if (!GcovBuffer.readInt(HistVal))
|
|
return sampleprof_error::truncated;
|
|
|
|
if (HistVal != HIST_TYPE_INDIR_CALL_TOPN)
|
|
return sampleprof_error::malformed;
|
|
|
|
uint64_t TargetIdx;
|
|
if (!GcovBuffer.readInt64(TargetIdx))
|
|
return sampleprof_error::truncated;
|
|
StringRef TargetName(Names[TargetIdx]);
|
|
|
|
uint64_t TargetCount;
|
|
if (!GcovBuffer.readInt64(TargetCount))
|
|
return sampleprof_error::truncated;
|
|
|
|
if (Update)
|
|
FProfile->addCalledTargetSamples(LineOffset, Discriminator,
|
|
TargetName, TargetCount);
|
|
}
|
|
}
|
|
|
|
// Process all the inlined callers into the current function. These
|
|
// are all the callsites that were inlined into this function.
|
|
for (uint32_t I = 0; I < NumCallsites; I++) {
|
|
// The offset is encoded as:
|
|
// high 16 bits: line offset to the start of the function.
|
|
// low 16 bits: discriminator.
|
|
uint32_t Offset;
|
|
if (!GcovBuffer.readInt(Offset))
|
|
return sampleprof_error::truncated;
|
|
InlineCallStack NewStack;
|
|
NewStack.push_back(FProfile);
|
|
llvm::append_range(NewStack, InlineStack);
|
|
if (std::error_code EC = readOneFunctionProfile(NewStack, Update, Offset))
|
|
return EC;
|
|
}
|
|
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
/// Read a GCC AutoFDO profile.
|
|
///
|
|
/// This format is generated by the Linux Perf conversion tool at
|
|
/// https://github.com/google/autofdo.
|
|
std::error_code SampleProfileReaderGCC::readImpl() {
|
|
// Read the string table.
|
|
if (std::error_code EC = readNameTable())
|
|
return EC;
|
|
|
|
// Read the source profile.
|
|
if (std::error_code EC = readFunctionProfiles())
|
|
return EC;
|
|
|
|
return sampleprof_error::success;
|
|
}
|
|
|
|
bool SampleProfileReaderGCC::hasFormat(const MemoryBuffer &Buffer) {
|
|
StringRef Magic(reinterpret_cast<const char *>(Buffer.getBufferStart()));
|
|
return Magic == "adcg*704";
|
|
}
|
|
|
|
void SampleProfileReaderItaniumRemapper::applyRemapping(LLVMContext &Ctx) {
|
|
// If the reader uses MD5 to represent string, we can't remap it because
|
|
// we don't know what the original function names were.
|
|
if (Reader.useMD5()) {
|
|
Ctx.diagnose(DiagnosticInfoSampleProfile(
|
|
Reader.getBuffer()->getBufferIdentifier(),
|
|
"Profile data remapping cannot be applied to profile data "
|
|
"in compact format (original mangled names are not available).",
|
|
DS_Warning));
|
|
return;
|
|
}
|
|
|
|
// CSSPGO-TODO: Remapper is not yet supported.
|
|
// We will need to remap the entire context string.
|
|
assert(Remappings && "should be initialized while creating remapper");
|
|
for (auto &Sample : Reader.getProfiles()) {
|
|
DenseSet<StringRef> NamesInSample;
|
|
Sample.second.findAllNames(NamesInSample);
|
|
for (auto &Name : NamesInSample)
|
|
if (auto Key = Remappings->insert(Name))
|
|
NameMap.insert({Key, Name});
|
|
}
|
|
|
|
RemappingApplied = true;
|
|
}
|
|
|
|
Optional<StringRef>
|
|
SampleProfileReaderItaniumRemapper::lookUpNameInProfile(StringRef Fname) {
|
|
if (auto Key = Remappings->lookup(Fname))
|
|
return NameMap.lookup(Key);
|
|
return None;
|
|
}
|
|
|
|
/// Prepare a memory buffer for the contents of \p Filename.
|
|
///
|
|
/// \returns an error code indicating the status of the buffer.
|
|
static ErrorOr<std::unique_ptr<MemoryBuffer>>
|
|
setupMemoryBuffer(const Twine &Filename) {
|
|
auto BufferOrErr = MemoryBuffer::getFileOrSTDIN(Filename);
|
|
if (std::error_code EC = BufferOrErr.getError())
|
|
return EC;
|
|
auto Buffer = std::move(BufferOrErr.get());
|
|
|
|
// Sanity check the file.
|
|
if (uint64_t(Buffer->getBufferSize()) > std::numeric_limits<uint32_t>::max())
|
|
return sampleprof_error::too_large;
|
|
|
|
return std::move(Buffer);
|
|
}
|
|
|
|
/// Create a sample profile reader based on the format of the input file.
|
|
///
|
|
/// \param Filename The file to open.
|
|
///
|
|
/// \param C The LLVM context to use to emit diagnostics.
|
|
///
|
|
/// \param RemapFilename The file used for profile remapping.
|
|
///
|
|
/// \returns an error code indicating the status of the created reader.
|
|
ErrorOr<std::unique_ptr<SampleProfileReader>>
|
|
SampleProfileReader::create(const std::string Filename, LLVMContext &C,
|
|
const std::string RemapFilename) {
|
|
auto BufferOrError = setupMemoryBuffer(Filename);
|
|
if (std::error_code EC = BufferOrError.getError())
|
|
return EC;
|
|
return create(BufferOrError.get(), C, RemapFilename);
|
|
}
|
|
|
|
/// Create a sample profile remapper from the given input, to remap the
|
|
/// function names in the given profile data.
|
|
///
|
|
/// \param Filename The file to open.
|
|
///
|
|
/// \param Reader The profile reader the remapper is going to be applied to.
|
|
///
|
|
/// \param C The LLVM context to use to emit diagnostics.
|
|
///
|
|
/// \returns an error code indicating the status of the created reader.
|
|
ErrorOr<std::unique_ptr<SampleProfileReaderItaniumRemapper>>
|
|
SampleProfileReaderItaniumRemapper::create(const std::string Filename,
|
|
SampleProfileReader &Reader,
|
|
LLVMContext &C) {
|
|
auto BufferOrError = setupMemoryBuffer(Filename);
|
|
if (std::error_code EC = BufferOrError.getError())
|
|
return EC;
|
|
return create(BufferOrError.get(), Reader, C);
|
|
}
|
|
|
|
/// Create a sample profile remapper from the given input, to remap the
|
|
/// function names in the given profile data.
|
|
///
|
|
/// \param B The memory buffer to create the reader from (assumes ownership).
|
|
///
|
|
/// \param C The LLVM context to use to emit diagnostics.
|
|
///
|
|
/// \param Reader The profile reader the remapper is going to be applied to.
|
|
///
|
|
/// \returns an error code indicating the status of the created reader.
|
|
ErrorOr<std::unique_ptr<SampleProfileReaderItaniumRemapper>>
|
|
SampleProfileReaderItaniumRemapper::create(std::unique_ptr<MemoryBuffer> &B,
|
|
SampleProfileReader &Reader,
|
|
LLVMContext &C) {
|
|
auto Remappings = std::make_unique<SymbolRemappingReader>();
|
|
if (Error E = Remappings->read(*B.get())) {
|
|
handleAllErrors(
|
|
std::move(E), [&](const SymbolRemappingParseError &ParseError) {
|
|
C.diagnose(DiagnosticInfoSampleProfile(B->getBufferIdentifier(),
|
|
ParseError.getLineNum(),
|
|
ParseError.getMessage()));
|
|
});
|
|
return sampleprof_error::malformed;
|
|
}
|
|
|
|
return std::make_unique<SampleProfileReaderItaniumRemapper>(
|
|
std::move(B), std::move(Remappings), Reader);
|
|
}
|
|
|
|
/// Create a sample profile reader based on the format of the input data.
|
|
///
|
|
/// \param B The memory buffer to create the reader from (assumes ownership).
|
|
///
|
|
/// \param C The LLVM context to use to emit diagnostics.
|
|
///
|
|
/// \param RemapFilename The file used for profile remapping.
|
|
///
|
|
/// \returns an error code indicating the status of the created reader.
|
|
ErrorOr<std::unique_ptr<SampleProfileReader>>
|
|
SampleProfileReader::create(std::unique_ptr<MemoryBuffer> &B, LLVMContext &C,
|
|
const std::string RemapFilename) {
|
|
std::unique_ptr<SampleProfileReader> Reader;
|
|
if (SampleProfileReaderRawBinary::hasFormat(*B))
|
|
Reader.reset(new SampleProfileReaderRawBinary(std::move(B), C));
|
|
else if (SampleProfileReaderExtBinary::hasFormat(*B))
|
|
Reader.reset(new SampleProfileReaderExtBinary(std::move(B), C));
|
|
else if (SampleProfileReaderCompactBinary::hasFormat(*B))
|
|
Reader.reset(new SampleProfileReaderCompactBinary(std::move(B), C));
|
|
else if (SampleProfileReaderGCC::hasFormat(*B))
|
|
Reader.reset(new SampleProfileReaderGCC(std::move(B), C));
|
|
else if (SampleProfileReaderText::hasFormat(*B))
|
|
Reader.reset(new SampleProfileReaderText(std::move(B), C));
|
|
else
|
|
return sampleprof_error::unrecognized_format;
|
|
|
|
if (!RemapFilename.empty()) {
|
|
auto ReaderOrErr =
|
|
SampleProfileReaderItaniumRemapper::create(RemapFilename, *Reader, C);
|
|
if (std::error_code EC = ReaderOrErr.getError()) {
|
|
std::string Msg = "Could not create remapper: " + EC.message();
|
|
C.diagnose(DiagnosticInfoSampleProfile(RemapFilename, Msg));
|
|
return EC;
|
|
}
|
|
Reader->Remapper = std::move(ReaderOrErr.get());
|
|
}
|
|
|
|
FunctionSamples::Format = Reader->getFormat();
|
|
if (std::error_code EC = Reader->readHeader()) {
|
|
return EC;
|
|
}
|
|
|
|
return std::move(Reader);
|
|
}
|
|
|
|
// For text and GCC file formats, we compute the summary after reading the
|
|
// profile. Binary format has the profile summary in its header.
|
|
void SampleProfileReader::computeSummary() {
|
|
SampleProfileSummaryBuilder Builder(ProfileSummaryBuilder::DefaultCutoffs);
|
|
Summary = Builder.computeSummaryForProfiles(Profiles);
|
|
}
|