1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-21 03:53:04 +02:00
llvm-mirror/tools/dsymutil/MachODebugMapParser.cpp

530 lines
19 KiB
C++
Raw Normal View History

//===- tools/dsymutil/MachODebugMapParser.cpp - Parse STABS debug maps ----===//
//
// The LLVM Linker
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "BinaryHolder.h"
#include "DebugMap.h"
#include "dsymutil.h"
#include "llvm/ADT/Optional.h"
#include "llvm/Object/MachO.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/raw_ostream.h"
namespace {
using namespace llvm;
using namespace llvm::dsymutil;
using namespace llvm::object;
class MachODebugMapParser {
public:
MachODebugMapParser(StringRef BinaryPath, ArrayRef<std::string> Archs,
StringRef PathPrefix = "", bool Verbose = false)
: BinaryPath(BinaryPath), Archs(Archs.begin(), Archs.end()),
PathPrefix(PathPrefix), MainBinaryHolder(Verbose),
CurrentObjectHolder(Verbose), CurrentDebugMapObject(nullptr) {}
/// \brief Parses and returns the DebugMaps of the input binary.
/// The binary contains multiple maps in case it is a universal
/// binary.
/// \returns an error in case the provided BinaryPath doesn't exist
/// or isn't of a supported type.
ErrorOr<std::vector<std::unique_ptr<DebugMap>>> parse();
/// Walk the symbol table and dump it.
bool dumpStab();
private:
std::string BinaryPath;
SmallVector<StringRef, 1> Archs;
std::string PathPrefix;
/// Owns the MemoryBuffer for the main binary.
BinaryHolder MainBinaryHolder;
/// Map of the binary symbol addresses.
StringMap<uint64_t> MainBinarySymbolAddresses;
StringRef MainBinaryStrings;
/// The constructed DebugMap.
std::unique_ptr<DebugMap> Result;
/// Owns the MemoryBuffer for the currently handled object file.
BinaryHolder CurrentObjectHolder;
/// Map of the currently processed object file symbol addresses.
StringMap<Optional<uint64_t>> CurrentObjectAddresses;
/// Element of the debug map corresponfing to the current object file.
DebugMapObject *CurrentDebugMapObject;
/// Holds function info while function scope processing.
const char *CurrentFunctionName;
uint64_t CurrentFunctionAddress;
std::unique_ptr<DebugMap> parseOneBinary(const MachOObjectFile &MainBinary,
StringRef BinaryPath);
void
switchToNewDebugMapObject(StringRef Filename,
sys::TimePoint<std::chrono::seconds> Timestamp);
void resetParserState();
uint64_t getMainBinarySymbolAddress(StringRef Name);
std::vector<StringRef> getMainBinarySymbolNames(uint64_t Value);
void loadMainBinarySymbols(const MachOObjectFile &MainBinary);
void loadCurrentObjectFileSymbols(const object::MachOObjectFile &Obj);
void handleStabSymbolTableEntry(uint32_t StringIndex, uint8_t Type,
uint8_t SectionIndex, uint16_t Flags,
uint64_t Value);
template <typename STEType> void handleStabDebugMapEntry(const STEType &STE) {
handleStabSymbolTableEntry(STE.n_strx, STE.n_type, STE.n_sect, STE.n_desc,
STE.n_value);
}
/// Dump the symbol table output header.
void dumpSymTabHeader(raw_ostream &OS, StringRef Arch);
/// Dump the contents of nlist entries.
void dumpSymTabEntry(raw_ostream &OS, uint64_t Index, uint32_t StringIndex,
uint8_t Type, uint8_t SectionIndex, uint16_t Flags,
uint64_t Value);
template <typename STEType>
void dumpSymTabEntry(raw_ostream &OS, uint64_t Index, const STEType &STE) {
dumpSymTabEntry(OS, Index, STE.n_strx, STE.n_type, STE.n_sect, STE.n_desc,
STE.n_value);
}
void dumpOneBinaryStab(const MachOObjectFile &MainBinary,
StringRef BinaryPath);
};
static void Warning(const Twine &Msg) { errs() << "warning: " + Msg + "\n"; }
} // anonymous namespace
/// Reset the parser state coresponding to the current object
/// file. This is to be called after an object file is finished
/// processing.
void MachODebugMapParser::resetParserState() {
CurrentObjectAddresses.clear();
CurrentDebugMapObject = nullptr;
}
/// Create a new DebugMapObject. This function resets the state of the
/// parser that was referring to the last object file and sets
/// everything up to add symbols to the new one.
void MachODebugMapParser::switchToNewDebugMapObject(
StringRef Filename, sys::TimePoint<std::chrono::seconds> Timestamp) {
resetParserState();
SmallString<80> Path(PathPrefix);
sys::path::append(Path, Filename);
auto MachOOrError =
CurrentObjectHolder.GetFilesAs<MachOObjectFile>(Path, Timestamp);
if (auto Error = MachOOrError.getError()) {
Warning(Twine("cannot open debug object \"") + Path.str() + "\": " +
Error.message() + "\n");
return;
}
auto ErrOrAchObj =
CurrentObjectHolder.GetAs<MachOObjectFile>(Result->getTriple());
if (auto Err = ErrOrAchObj.getError()) {
return Warning(Twine("cannot open debug object \"") + Path.str() + "\": " +
Err.message() + "\n");
}
CurrentDebugMapObject =
&Result->addDebugMapObject(Path, Timestamp, MachO::N_OSO);
loadCurrentObjectFileSymbols(*ErrOrAchObj);
}
static std::string getArchName(const object::MachOObjectFile &Obj) {
Triple T = Obj.getArchTriple();
return T.getArchName();
}
std::unique_ptr<DebugMap>
MachODebugMapParser::parseOneBinary(const MachOObjectFile &MainBinary,
StringRef BinaryPath) {
loadMainBinarySymbols(MainBinary);
Result = make_unique<DebugMap>(MainBinary.getArchTriple(), BinaryPath);
MainBinaryStrings = MainBinary.getStringTableData();
for (const SymbolRef &Symbol : MainBinary.symbols()) {
const DataRefImpl &DRI = Symbol.getRawDataRefImpl();
if (MainBinary.is64Bit())
handleStabDebugMapEntry(MainBinary.getSymbol64TableEntry(DRI));
else
handleStabDebugMapEntry(MainBinary.getSymbolTableEntry(DRI));
}
resetParserState();
return std::move(Result);
}
// Table that maps Darwin's Mach-O stab constants to strings to allow printing.
// llvm-nm has very similar code, the strings used here are however slightly
// different and part of the interface of dsymutil (some project's build-systems
// parse the ouptut of dsymutil -s), thus they shouldn't be changed.
struct DarwinStabName {
uint8_t NType;
const char *Name;
};
static const struct DarwinStabName DarwinStabNames[] = {
{MachO::N_GSYM, "N_GSYM"}, {MachO::N_FNAME, "N_FNAME"},
{MachO::N_FUN, "N_FUN"}, {MachO::N_STSYM, "N_STSYM"},
{MachO::N_LCSYM, "N_LCSYM"}, {MachO::N_BNSYM, "N_BNSYM"},
{MachO::N_PC, "N_PC"}, {MachO::N_AST, "N_AST"},
{MachO::N_OPT, "N_OPT"}, {MachO::N_RSYM, "N_RSYM"},
{MachO::N_SLINE, "N_SLINE"}, {MachO::N_ENSYM, "N_ENSYM"},
{MachO::N_SSYM, "N_SSYM"}, {MachO::N_SO, "N_SO"},
{MachO::N_OSO, "N_OSO"}, {MachO::N_LSYM, "N_LSYM"},
{MachO::N_BINCL, "N_BINCL"}, {MachO::N_SOL, "N_SOL"},
{MachO::N_PARAMS, "N_PARAM"}, {MachO::N_VERSION, "N_VERS"},
{MachO::N_OLEVEL, "N_OLEV"}, {MachO::N_PSYM, "N_PSYM"},
{MachO::N_EINCL, "N_EINCL"}, {MachO::N_ENTRY, "N_ENTRY"},
{MachO::N_LBRAC, "N_LBRAC"}, {MachO::N_EXCL, "N_EXCL"},
{MachO::N_RBRAC, "N_RBRAC"}, {MachO::N_BCOMM, "N_BCOMM"},
{MachO::N_ECOMM, "N_ECOMM"}, {MachO::N_ECOML, "N_ECOML"},
{MachO::N_LENG, "N_LENG"}, {0, nullptr}};
static const char *getDarwinStabString(uint8_t NType) {
for (unsigned i = 0; DarwinStabNames[i].Name; i++) {
if (DarwinStabNames[i].NType == NType)
return DarwinStabNames[i].Name;
}
return nullptr;
}
void MachODebugMapParser::dumpSymTabHeader(raw_ostream &OS, StringRef Arch) {
OS << "-----------------------------------"
"-----------------------------------\n";
OS << "Symbol table for: '" << BinaryPath << "' (" << Arch.data() << ")\n";
OS << "-----------------------------------"
"-----------------------------------\n";
OS << "Index n_strx n_type n_sect n_desc n_value\n";
OS << "======== -------- ------------------ ------ ------ ----------------\n";
}
void MachODebugMapParser::dumpSymTabEntry(raw_ostream &OS, uint64_t Index,
uint32_t StringIndex, uint8_t Type,
uint8_t SectionIndex, uint16_t Flags,
uint64_t Value) {
// Index
OS << '[' << format_decimal(Index, 6) << "] "
// n_strx
<< format_hex_no_prefix(StringIndex, 8) << ' '
// n_type...
<< format_hex_no_prefix(Type, 2) << " (";
if (Type & MachO::N_STAB)
OS << left_justify(getDarwinStabString(Type), 13);
else {
if (Type & MachO::N_PEXT)
OS << "PEXT ";
else
OS << " ";
switch (Type & MachO::N_TYPE) {
case MachO::N_UNDF: // 0x0 undefined, n_sect == NO_SECT
OS << "UNDF";
break;
case MachO::N_ABS: // 0x2 absolute, n_sect == NO_SECT
OS << "ABS ";
break;
case MachO::N_SECT: // 0xe defined in section number n_sect
OS << "SECT";
break;
case MachO::N_PBUD: // 0xc prebound undefined (defined in a dylib)
OS << "PBUD";
break;
case MachO::N_INDR: // 0xa indirect
OS << "INDR";
break;
default:
OS << format_hex_no_prefix(Type, 2) << " ";
break;
}
if (Type & MachO::N_EXT)
OS << " EXT";
else
OS << " ";
}
OS << ") "
// n_sect
<< format_hex_no_prefix(SectionIndex, 2) << " "
// n_desc
<< format_hex_no_prefix(Flags, 4) << " "
// n_value
<< format_hex_no_prefix(Value, 16);
const char *Name = &MainBinaryStrings.data()[StringIndex];
if (Name && Name[0])
OS << " '" << Name << "'";
OS << "\n";
}
void MachODebugMapParser::dumpOneBinaryStab(const MachOObjectFile &MainBinary,
StringRef BinaryPath) {
loadMainBinarySymbols(MainBinary);
MainBinaryStrings = MainBinary.getStringTableData();
raw_ostream &OS(llvm::outs());
dumpSymTabHeader(OS, getArchName(MainBinary));
uint64_t Idx = 0;
for (const SymbolRef &Symbol : MainBinary.symbols()) {
const DataRefImpl &DRI = Symbol.getRawDataRefImpl();
if (MainBinary.is64Bit())
dumpSymTabEntry(OS, Idx, MainBinary.getSymbol64TableEntry(DRI));
else
dumpSymTabEntry(OS, Idx, MainBinary.getSymbolTableEntry(DRI));
Idx++;
}
OS << "\n\n";
resetParserState();
}
static bool shouldLinkArch(SmallVectorImpl<StringRef> &Archs, StringRef Arch) {
if (Archs.empty() || is_contained(Archs, "all") || is_contained(Archs, "*"))
return true;
if (Arch.startswith("arm") && Arch != "arm64" && is_contained(Archs, "arm"))
return true;
SmallString<16> ArchName = Arch;
if (Arch.startswith("thumb"))
ArchName = ("arm" + Arch.substr(5)).str();
return is_contained(Archs, ArchName);
}
bool MachODebugMapParser::dumpStab() {
auto MainBinOrError =
MainBinaryHolder.GetFilesAs<MachOObjectFile>(BinaryPath);
if (auto Error = MainBinOrError.getError()) {
llvm::errs() << "Cannot get '" << BinaryPath
<< "' as MachO file: " << Error.message() << "\n";
return false;
}
for (const auto *Binary : *MainBinOrError)
if (shouldLinkArch(Archs, Binary->getArchTriple().getArchName()))
dumpOneBinaryStab(*Binary, BinaryPath);
return true;
}
/// This main parsing routine tries to open the main binary and if
/// successful iterates over the STAB entries. The real parsing is
/// done in handleStabSymbolTableEntry.
ErrorOr<std::vector<std::unique_ptr<DebugMap>>> MachODebugMapParser::parse() {
auto MainBinOrError =
MainBinaryHolder.GetFilesAs<MachOObjectFile>(BinaryPath);
if (auto Error = MainBinOrError.getError())
return Error;
std::vector<std::unique_ptr<DebugMap>> Results;
for (const auto *Binary : *MainBinOrError)
if (shouldLinkArch(Archs, Binary->getArchTriple().getArchName()))
Results.push_back(parseOneBinary(*Binary, BinaryPath));
return std::move(Results);
}
/// Interpret the STAB entries to fill the DebugMap.
void MachODebugMapParser::handleStabSymbolTableEntry(uint32_t StringIndex,
uint8_t Type,
uint8_t SectionIndex,
uint16_t Flags,
uint64_t Value) {
if (!(Type & MachO::N_STAB))
return;
const char *Name = &MainBinaryStrings.data()[StringIndex];
// An N_OSO entry represents the start of a new object file description.
if (Type == MachO::N_OSO)
return switchToNewDebugMapObject(Name, sys::toTimePoint(Value));
if (Type == MachO::N_AST) {
SmallString<80> Path(PathPrefix);
sys::path::append(Path, Name);
Result->addDebugMapObject(Path, sys::toTimePoint(Value), Type);
return;
}
// If the last N_OSO object file wasn't found,
// CurrentDebugMapObject will be null. Do not update anything
// until we find the next valid N_OSO entry.
if (!CurrentDebugMapObject)
return;
uint32_t Size = 0;
switch (Type) {
case MachO::N_GSYM:
// This is a global variable. We need to query the main binary
// symbol table to find its address as it might not be in the
// debug map (for common symbols).
Value = getMainBinarySymbolAddress(Name);
break;
case MachO::N_FUN:
// Functions are scopes in STABS. They have an end marker that
// contains the function size.
if (Name[0] == '\0') {
Size = Value;
Value = CurrentFunctionAddress;
Name = CurrentFunctionName;
break;
} else {
CurrentFunctionName = Name;
CurrentFunctionAddress = Value;
return;
}
case MachO::N_STSYM:
break;
default:
return;
}
auto ObjectSymIt = CurrentObjectAddresses.find(Name);
// If the name of a (non-static) symbol is not in the current object, we
// check all its aliases from the main binary.
if (ObjectSymIt == CurrentObjectAddresses.end() && Type != MachO::N_STSYM) {
for (const auto &Alias : getMainBinarySymbolNames(Value)) {
ObjectSymIt = CurrentObjectAddresses.find(Alias);
if (ObjectSymIt != CurrentObjectAddresses.end())
break;
}
}
if (ObjectSymIt == CurrentObjectAddresses.end())
return Warning("could not find object file symbol for symbol " +
Twine(Name));
if (!CurrentDebugMapObject->addSymbol(Name, ObjectSymIt->getValue(), Value,
Size))
return Warning(Twine("failed to insert symbol '") + Name +
"' in the debug map.");
}
/// Load the current object file symbols into CurrentObjectAddresses.
void MachODebugMapParser::loadCurrentObjectFileSymbols(
const object::MachOObjectFile &Obj) {
CurrentObjectAddresses.clear();
for (auto Sym : Obj.symbols()) {
uint64_t Addr = Sym.getValue();
Thread Expected<...> up from libObject’s getName() for symbols to allow llvm-objdump to produce a good error message. Produce another specific error message for a malformed Mach-O file when a symbol’s string index is past the end of the string table. The existing test case in test/Object/macho-invalid.test for macho-invalid-symbol-name-past-eof now reports the error with the message indicating that a symbol at a specific index has a bad sting index and that bad string index value. Again converting interfaces to Expected<> from ErrorOr<> does involve touching a number of places. Where the existing code reported the error with a string message or an error code it was converted to do the same. There is some code for this that could be factored into a routine but I would like to leave that for the code owners post-commit to do as they want for handling an llvm::Error. An example of how this could be done is shown in the diff in lib/ExecutionEngine/RuntimeDyld/RuntimeDyldImpl.h which had a Check() routine already for std::error_code so I added one like it for llvm::Error . Also there some were bugs in the existing code that did not deal with the old ErrorOr<> return values.  So now with Expected<> since they must be checked and the error handled, I added a TODO and a comment: “// TODO: Actually report errors helpfully” and a call something like consumeError(NameOrErr.takeError()) so the buggy code will not crash since needed to deal with the Error. Note there fixes needed to lld that goes along with this that I will commit right after this. So expect lld not to built after this commit and before the next one. llvm-svn: 266919
2016-04-20 23:24:34 +02:00
Expected<StringRef> Name = Sym.getName();
if (!Name) {
// TODO: Actually report errors helpfully.
consumeError(Name.takeError());
continue;
Thread Expected<...> up from libObject’s getName() for symbols to allow llvm-objdump to produce a good error message. Produce another specific error message for a malformed Mach-O file when a symbol’s string index is past the end of the string table. The existing test case in test/Object/macho-invalid.test for macho-invalid-symbol-name-past-eof now reports the error with the message indicating that a symbol at a specific index has a bad sting index and that bad string index value. Again converting interfaces to Expected<> from ErrorOr<> does involve touching a number of places. Where the existing code reported the error with a string message or an error code it was converted to do the same. There is some code for this that could be factored into a routine but I would like to leave that for the code owners post-commit to do as they want for handling an llvm::Error. An example of how this could be done is shown in the diff in lib/ExecutionEngine/RuntimeDyld/RuntimeDyldImpl.h which had a Check() routine already for std::error_code so I added one like it for llvm::Error . Also there some were bugs in the existing code that did not deal with the old ErrorOr<> return values.  So now with Expected<> since they must be checked and the error handled, I added a TODO and a comment: “// TODO: Actually report errors helpfully” and a call something like consumeError(NameOrErr.takeError()) so the buggy code will not crash since needed to deal with the Error. Note there fixes needed to lld that goes along with this that I will commit right after this. So expect lld not to built after this commit and before the next one. llvm-svn: 266919
2016-04-20 23:24:34 +02:00
}
// The value of some categories of symbols isn't meaningful. For
// example common symbols store their size in the value field, not
// their address. Absolute symbols have a fixed address that can
// conflict with standard symbols. These symbols (especially the
// common ones), might still be referenced by relocations. These
// relocations will use the symbol itself, and won't need an
// object file address. The object file address field is optional
// in the DebugMap, leave it unassigned for these symbols.
if (Sym.getFlags() & (SymbolRef::SF_Absolute | SymbolRef::SF_Common))
CurrentObjectAddresses[*Name] = None;
else
CurrentObjectAddresses[*Name] = Addr;
}
}
/// Lookup a symbol address in the main binary symbol table. The
/// parser only needs to query common symbols, thus not every symbol's
/// address is available through this function.
uint64_t MachODebugMapParser::getMainBinarySymbolAddress(StringRef Name) {
auto Sym = MainBinarySymbolAddresses.find(Name);
if (Sym == MainBinarySymbolAddresses.end())
return 0;
return Sym->second;
}
/// Get all symbol names in the main binary for the given value.
std::vector<StringRef>
MachODebugMapParser::getMainBinarySymbolNames(uint64_t Value) {
std::vector<StringRef> Names;
for (const auto &Entry : MainBinarySymbolAddresses) {
if (Entry.second == Value)
Names.push_back(Entry.first());
}
return Names;
}
/// Load the interesting main binary symbols' addresses into
/// MainBinarySymbolAddresses.
void MachODebugMapParser::loadMainBinarySymbols(
const MachOObjectFile &MainBinary) {
section_iterator Section = MainBinary.section_end();
MainBinarySymbolAddresses.clear();
for (const auto &Sym : MainBinary.symbols()) {
Expected<SymbolRef::Type> TypeOrErr = Sym.getType();
if (!TypeOrErr) {
// TODO: Actually report errors helpfully.
consumeError(TypeOrErr.takeError());
Fix a crash in running llvm-objdump -t with an invalid Mach-O file already in the test suite. While this is not really an interesting tool and option to run on a Mach-O file to show the symbol table in a generic libObject format it shouldn’t crash. The reason for the crash was in MachOObjectFile::getSymbolType() when it was calling MachOObjectFile::getSymbolSection() without checking its return value for the error case. What makes this fix require a fair bit of diffs is that the method getSymbolType() is in the class ObjectFile defined without an ErrorOr<> so I needed to add that all the sub classes.  And all of the uses needed to be updated and the return value needed to be checked for the error case. The MachOObjectFile version of getSymbolType() “can” get an error in trying to come up with the libObject’s internal SymbolRef::Type when the Mach-O symbol symbol type is an N_SECT type because the code is trying to select from the SymbolRef::ST_Data or SymbolRef::ST_Function values for the SymbolRef::Type. And it needs the Mach-O section to use isData() and isBSS to determine if it will return SymbolRef::ST_Data. One other possible fix I considered is to simply return SymbolRef::ST_Other when MachOObjectFile::getSymbolSection() returned an error. But since in the past when I did such changes that “ate an error in the libObject code” I was asked instead to push the error out of the libObject code I chose not to implement the fix this way. As currently written both the COFF and ELF versions of getSymbolType() can’t get an error. But if isReservedSectionNumber() wanted to check for the two known negative values rather than allowing all negative values or the code wanted to add the same check as in getSymbolAddress() to use getSection() and check for the error then these versions of getSymbolType() could return errors. At the end of the day the error printed now is the generic “Invalid data was encountered while parsing the file” for object_error::parse_failed. In the future when we thread Lang’s new TypedError for recoverable error handling though libObject this will improve. And where the added // Diagnostic(… comment is, it would be changed to produce and error message like “bad section index (42) for symbol at index 8” for this case. llvm-svn: 264187
2016-03-23 21:27:00 +01:00
continue;
}
Fix a crash in running llvm-objdump -t with an invalid Mach-O file already in the test suite. While this is not really an interesting tool and option to run on a Mach-O file to show the symbol table in a generic libObject format it shouldn’t crash. The reason for the crash was in MachOObjectFile::getSymbolType() when it was calling MachOObjectFile::getSymbolSection() without checking its return value for the error case. What makes this fix require a fair bit of diffs is that the method getSymbolType() is in the class ObjectFile defined without an ErrorOr<> so I needed to add that all the sub classes.  And all of the uses needed to be updated and the return value needed to be checked for the error case. The MachOObjectFile version of getSymbolType() “can” get an error in trying to come up with the libObject’s internal SymbolRef::Type when the Mach-O symbol symbol type is an N_SECT type because the code is trying to select from the SymbolRef::ST_Data or SymbolRef::ST_Function values for the SymbolRef::Type. And it needs the Mach-O section to use isData() and isBSS to determine if it will return SymbolRef::ST_Data. One other possible fix I considered is to simply return SymbolRef::ST_Other when MachOObjectFile::getSymbolSection() returned an error. But since in the past when I did such changes that “ate an error in the libObject code” I was asked instead to push the error out of the libObject code I chose not to implement the fix this way. As currently written both the COFF and ELF versions of getSymbolType() can’t get an error. But if isReservedSectionNumber() wanted to check for the two known negative values rather than allowing all negative values or the code wanted to add the same check as in getSymbolAddress() to use getSection() and check for the error then these versions of getSymbolType() could return errors. At the end of the day the error printed now is the generic “Invalid data was encountered while parsing the file” for object_error::parse_failed. In the future when we thread Lang’s new TypedError for recoverable error handling though libObject this will improve. And where the added // Diagnostic(… comment is, it would be changed to produce and error message like “bad section index (42) for symbol at index 8” for this case. llvm-svn: 264187
2016-03-23 21:27:00 +01:00
SymbolRef::Type Type = *TypeOrErr;
// Skip undefined and STAB entries.
if ((Type == SymbolRef::ST_Debug) || (Type == SymbolRef::ST_Unknown))
continue;
// The only symbols of interest are the global variables. These
// are the only ones that need to be queried because the address
// of common data won't be described in the debug map. All other
// addresses should be fetched for the debug map.
if (!(Sym.getFlags() & SymbolRef::SF_Global))
continue;
Expected<section_iterator> SectionOrErr = Sym.getSection();
if (!SectionOrErr) {
// TODO: Actually report errors helpfully.
consumeError(SectionOrErr.takeError());
continue;
}
Section = *SectionOrErr;
if (Section == MainBinary.section_end() || Section->isText())
continue;
uint64_t Addr = Sym.getValue();
Thread Expected<...> up from libObject’s getName() for symbols to allow llvm-objdump to produce a good error message. Produce another specific error message for a malformed Mach-O file when a symbol’s string index is past the end of the string table. The existing test case in test/Object/macho-invalid.test for macho-invalid-symbol-name-past-eof now reports the error with the message indicating that a symbol at a specific index has a bad sting index and that bad string index value. Again converting interfaces to Expected<> from ErrorOr<> does involve touching a number of places. Where the existing code reported the error with a string message or an error code it was converted to do the same. There is some code for this that could be factored into a routine but I would like to leave that for the code owners post-commit to do as they want for handling an llvm::Error. An example of how this could be done is shown in the diff in lib/ExecutionEngine/RuntimeDyld/RuntimeDyldImpl.h which had a Check() routine already for std::error_code so I added one like it for llvm::Error . Also there some were bugs in the existing code that did not deal with the old ErrorOr<> return values.  So now with Expected<> since they must be checked and the error handled, I added a TODO and a comment: “// TODO: Actually report errors helpfully” and a call something like consumeError(NameOrErr.takeError()) so the buggy code will not crash since needed to deal with the Error. Note there fixes needed to lld that goes along with this that I will commit right after this. So expect lld not to built after this commit and before the next one. llvm-svn: 266919
2016-04-20 23:24:34 +02:00
Expected<StringRef> NameOrErr = Sym.getName();
if (!NameOrErr) {
// TODO: Actually report errors helpfully.
consumeError(NameOrErr.takeError());
continue;
Thread Expected<...> up from libObject’s getName() for symbols to allow llvm-objdump to produce a good error message. Produce another specific error message for a malformed Mach-O file when a symbol’s string index is past the end of the string table. The existing test case in test/Object/macho-invalid.test for macho-invalid-symbol-name-past-eof now reports the error with the message indicating that a symbol at a specific index has a bad sting index and that bad string index value. Again converting interfaces to Expected<> from ErrorOr<> does involve touching a number of places. Where the existing code reported the error with a string message or an error code it was converted to do the same. There is some code for this that could be factored into a routine but I would like to leave that for the code owners post-commit to do as they want for handling an llvm::Error. An example of how this could be done is shown in the diff in lib/ExecutionEngine/RuntimeDyld/RuntimeDyldImpl.h which had a Check() routine already for std::error_code so I added one like it for llvm::Error . Also there some were bugs in the existing code that did not deal with the old ErrorOr<> return values.  So now with Expected<> since they must be checked and the error handled, I added a TODO and a comment: “// TODO: Actually report errors helpfully” and a call something like consumeError(NameOrErr.takeError()) so the buggy code will not crash since needed to deal with the Error. Note there fixes needed to lld that goes along with this that I will commit right after this. So expect lld not to built after this commit and before the next one. llvm-svn: 266919
2016-04-20 23:24:34 +02:00
}
StringRef Name = *NameOrErr;
if (Name.size() == 0 || Name[0] == '\0')
continue;
MainBinarySymbolAddresses[Name] = Addr;
}
}
namespace llvm {
namespace dsymutil {
llvm::ErrorOr<std::vector<std::unique_ptr<DebugMap>>>
parseDebugMap(StringRef InputFile, ArrayRef<std::string> Archs,
StringRef PrependPath, bool Verbose, bool InputIsYAML) {
if (!InputIsYAML) {
MachODebugMapParser Parser(InputFile, Archs, PrependPath, Verbose);
return Parser.parse();
} else {
return DebugMap::parseYAMLDebugMap(InputFile, PrependPath, Verbose);
}
}
bool dumpStab(StringRef InputFile, ArrayRef<std::string> Archs,
StringRef PrependPath) {
MachODebugMapParser Parser(InputFile, Archs, PrependPath, false);
return Parser.dumpStab();
}
} // namespace dsymutil
} // namespace llvm