llvm-project/llvm/tools/llvm-objdump/llvm-objdump.cpp

2091 lines
71 KiB
C++
Raw Normal View History

2011-01-20 14:39:06 +08:00
//===-- llvm-objdump.cpp - Object file dumping utility for llvm -----------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This program is a utility that works like binutils "objdump", that is, it
// dumps out a plethora of information about an object file depending on the
// flags.
//
// The flags and output of this program should be near identical to those of
// binutils objdump.
//
2011-01-20 14:39:06 +08:00
//===----------------------------------------------------------------------===//
#include "llvm-objdump.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringExtras.h"
2011-01-20 14:39:06 +08:00
#include "llvm/ADT/Triple.h"
#include "llvm/CodeGen/FaultMaps.h"
#include "llvm/DebugInfo/DWARF/DWARFContext.h"
#include "llvm/DebugInfo/Symbolize/Symbolize.h"
2011-01-20 14:39:06 +08:00
#include "llvm/MC/MCAsmInfo.h"
Add MCSymbolizer for symbolic/annotated disassembly. This is a basic first step towards symbolization of disassembled instructions. This used to be done using externally provided (C API) callbacks. This patch introduces: - the MCSymbolizer class, that mimics the same functions that were used in the X86 and ARM disassemblers to symbolize immediate operands and to annotate loads based off PC (for things like c string literals). - the MCExternalSymbolizer class, which implements the old C API. - the MCRelocationInfo class, which provides a way for targets to translate relocations (either object::RelocationRef, or disassembler C API VariantKinds) to MCExprs. - the MCObjectSymbolizer class, which does symbolization using what it finds in an object::ObjectFile. This makes simple symbolization (with no fancy relocation stuff) work for all object formats! - x86-64 Mach-O and ELF MCRelocationInfos. - A basic ARM Mach-O MCRelocationInfo, that provides just enough to support the C API VariantKinds. Most of what works in otool (the only user of the old symbolization API that I know of) for x86-64 symbolic disassembly (-tvV) works, namely: - symbol references: call _foo; jmp 15 <_foo+50> - relocations: call _foo-_bar; call _foo-4 - __cf?string: leaq 193(%rip), %rax ## literal pool for "hello" Stub support is the main missing part (because libObject doesn't know, among other things, about mach-o indirect symbols). As for the MCSymbolizer API, instead of relying on the disassemblers to call the tryAdding* methods, maybe this could be done automagically using InstrInfo? For instance, even though PC-relative LEAs are used to get the address of string literals in a typical Mach-O file, a MOV would be used in an ELF file. And right now, the explicit symbolization only recognizes PC-relative LEAs. InstrInfo should have already have most of what is needed to know what to symbolize, so this can definitely be improved. I'd also like to remove object::RelocationRef::getValueString (it seems only used by relocation printing in objdump), as simply printing the created MCExpr is definitely enough (and cleaner than string concats). llvm-svn: 182625
2013-05-24 08:39:57 +08:00
#include "llvm/MC/MCContext.h"
#include "llvm/MC/MCDisassembler/MCDisassembler.h"
#include "llvm/MC/MCDisassembler/MCRelocationInfo.h"
2011-01-20 14:39:06 +08:00
#include "llvm/MC/MCInst.h"
#include "llvm/MC/MCInstPrinter.h"
MC: Disassembled CFG reconstruction. This patch builds on some existing code to do CFG reconstruction from a disassembled binary: - MCModule represents the binary, and has a list of MCAtoms. - MCAtom represents either disassembled instructions (MCTextAtom), or contiguous data (MCDataAtom), and covers a specific range of addresses. - MCBasicBlock and MCFunction form the reconstructed CFG. An MCBB is backed by an MCTextAtom, and has the usual successors/predecessors. - MCObjectDisassembler creates a module from an ObjectFile using a disassembler. It first builds an atom for each section. It can also construct the CFG, and this splits the text atoms into basic blocks. MCModule and MCAtom were only sketched out; MCFunction and MCBB were implemented under the experimental "-cfg" llvm-objdump -macho option. This cleans them up for further use; llvm-objdump -d -cfg now generates graphviz files for each function found in the binary. In the future, MCObjectDisassembler may be the right place to do "intelligent" disassembly: for example, handling constant islands is just a matter of splitting the atom, using information that may be available in the ObjectFile. Also, better initial atom formation than just using sections is possible using symbols (and things like Mach-O's function_starts load command). This brings two minor regressions in llvm-objdump -macho -cfg: - The printing of a relocation's referenced symbol. - An annotation on loop BBs, i.e., which are their own successor. Relocation printing is replaced by the MCSymbolizer; the basic CFG annotation will be superseded by more related functionality. llvm-svn: 182628
2013-05-24 09:07:04 +08:00
#include "llvm/MC/MCInstrAnalysis.h"
#include "llvm/MC/MCInstrInfo.h"
Add MCSymbolizer for symbolic/annotated disassembly. This is a basic first step towards symbolization of disassembled instructions. This used to be done using externally provided (C API) callbacks. This patch introduces: - the MCSymbolizer class, that mimics the same functions that were used in the X86 and ARM disassemblers to symbolize immediate operands and to annotate loads based off PC (for things like c string literals). - the MCExternalSymbolizer class, which implements the old C API. - the MCRelocationInfo class, which provides a way for targets to translate relocations (either object::RelocationRef, or disassembler C API VariantKinds) to MCExprs. - the MCObjectSymbolizer class, which does symbolization using what it finds in an object::ObjectFile. This makes simple symbolization (with no fancy relocation stuff) work for all object formats! - x86-64 Mach-O and ELF MCRelocationInfos. - A basic ARM Mach-O MCRelocationInfo, that provides just enough to support the C API VariantKinds. Most of what works in otool (the only user of the old symbolization API that I know of) for x86-64 symbolic disassembly (-tvV) works, namely: - symbol references: call _foo; jmp 15 <_foo+50> - relocations: call _foo-_bar; call _foo-4 - __cf?string: leaq 193(%rip), %rax ## literal pool for "hello" Stub support is the main missing part (because libObject doesn't know, among other things, about mach-o indirect symbols). As for the MCSymbolizer API, instead of relying on the disassemblers to call the tryAdding* methods, maybe this could be done automagically using InstrInfo? For instance, even though PC-relative LEAs are used to get the address of string literals in a typical Mach-O file, a MOV would be used in an ELF file. And right now, the explicit symbolization only recognizes PC-relative LEAs. InstrInfo should have already have most of what is needed to know what to symbolize, so this can definitely be improved. I'd also like to remove object::RelocationRef::getValueString (it seems only used by relocation printing in objdump), as simply printing the created MCExpr is definitely enough (and cleaner than string concats). llvm-svn: 182625
2013-05-24 08:39:57 +08:00
#include "llvm/MC/MCObjectFileInfo.h"
#include "llvm/MC/MCRegisterInfo.h"
MC: Disassembled CFG reconstruction. This patch builds on some existing code to do CFG reconstruction from a disassembled binary: - MCModule represents the binary, and has a list of MCAtoms. - MCAtom represents either disassembled instructions (MCTextAtom), or contiguous data (MCDataAtom), and covers a specific range of addresses. - MCBasicBlock and MCFunction form the reconstructed CFG. An MCBB is backed by an MCTextAtom, and has the usual successors/predecessors. - MCObjectDisassembler creates a module from an ObjectFile using a disassembler. It first builds an atom for each section. It can also construct the CFG, and this splits the text atoms into basic blocks. MCModule and MCAtom were only sketched out; MCFunction and MCBB were implemented under the experimental "-cfg" llvm-objdump -macho option. This cleans them up for further use; llvm-objdump -d -cfg now generates graphviz files for each function found in the binary. In the future, MCObjectDisassembler may be the right place to do "intelligent" disassembly: for example, handling constant islands is just a matter of splitting the atom, using information that may be available in the ObjectFile. Also, better initial atom formation than just using sections is possible using symbols (and things like Mach-O's function_starts load command). This brings two minor regressions in llvm-objdump -macho -cfg: - The printing of a relocation's referenced symbol. - An annotation on loop BBs, i.e., which are their own successor. Relocation printing is replaced by the MCSymbolizer; the basic CFG annotation will be superseded by more related functionality. llvm-svn: 182628
2013-05-24 09:07:04 +08:00
#include "llvm/MC/MCSubtargetInfo.h"
#include "llvm/Object/Archive.h"
#include "llvm/Object/COFF.h"
#include "llvm/Object/COFFImportFile.h"
#include "llvm/Object/ELFObjectFile.h"
#include "llvm/Object/MachO.h"
#include "llvm/Object/ObjectFile.h"
#include "llvm/Support/Casting.h"
2011-01-20 14:39:06 +08:00
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/Errc.h"
#include "llvm/Support/FileSystem.h"
2011-01-20 14:39:06 +08:00
#include "llvm/Support/Format.h"
#include "llvm/Support/GraphWriter.h"
2011-01-20 14:39:06 +08:00
#include "llvm/Support/Host.h"
#include "llvm/Support/ManagedStatic.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/PrettyStackTrace.h"
#include "llvm/Support/Signals.h"
#include "llvm/Support/SourceMgr.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Support/TargetSelect.h"
2011-01-20 14:39:06 +08:00
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
#include <cctype>
2011-01-20 14:39:06 +08:00
#include <cstring>
#include <system_error>
#include <utility>
#include <unordered_map>
MC CFG: Add YAML MCModule representation to enable MC CFG testing. Like yaml ObjectFiles, this will be very useful for testing the MC CFG implementation (mostly MCObjectDisassembler), by matching the output with YAML, and for potential users of the MC CFG, by using it as an input. There isn't much to the actual format, it is just a serialization of the MCModule class. Of note: - Basic block references (pred/succ, ..) are represented by the BB's start address. - Just as in the MC CFG, instructions are MCInsts with a size. - Operands have a prefix representing the type (only register and immediate supported here). - Instruction opcodes are represented by their names; enum values aren't stable, enum names mostly are: usually, a change to a name would need lots of changes in the backend anyway. Same with registers. All in all, an example is better than 1000 words, here goes: A simple binary: Disassembly of section __TEXT,__text: _main: 100000f9c: 48 8b 46 08 movq 8(%rsi), %rax 100000fa0: 0f be 00 movsbl (%rax), %eax 100000fa3: 3b 04 25 48 00 00 00 cmpl 72, %eax 100000faa: 0f 8c 07 00 00 00 jl 7 <.Lend> 100000fb0: 2b 04 25 48 00 00 00 subl 72, %eax .Lend: 100000fb7: c3 ret And the (pretty verbose) generated YAML: --- Atoms: - StartAddress: 0x0000000100000F9C Size: 20 Type: Text Content: - Inst: MOV64rm Size: 4 Ops: [ RRAX, RRSI, I1, R, I8, R ] - Inst: MOVSX32rm8 Size: 3 Ops: [ REAX, RRAX, I1, R, I0, R ] - Inst: CMP32rm Size: 7 Ops: [ REAX, R, I1, R, I72, R ] - Inst: JL_4 Size: 6 Ops: [ I7 ] - StartAddress: 0x0000000100000FB0 Size: 7 Type: Text Content: - Inst: SUB32rm Size: 7 Ops: [ REAX, REAX, R, I1, R, I72, R ] - StartAddress: 0x0000000100000FB7 Size: 1 Type: Text Content: - Inst: RET Size: 1 Ops: [ ] Functions: - Name: __text BasicBlocks: - Address: 0x0000000100000F9C Preds: [ ] Succs: [ 0x0000000100000FB7, 0x0000000100000FB0 ] <snip> ... llvm-svn: 188890
2013-08-21 15:29:02 +08:00
2011-01-20 14:39:06 +08:00
using namespace llvm;
using namespace object;
static cl::list<std::string>
InputFilenames(cl::Positional, cl::desc("<input object files>"),cl::ZeroOrMore);
2011-01-20 14:39:06 +08:00
cl::opt<bool>
llvm::Disassemble("disassemble",
cl::desc("Display assembler mnemonics for the machine instructions"));
static cl::alias
Disassembled("d", cl::desc("Alias for --disassemble"),
cl::aliasopt(Disassemble));
cl::opt<bool>
llvm::DisassembleAll("disassemble-all",
cl::desc("Display assembler mnemonics for the machine instructions"));
static cl::alias
DisassembleAlld("D", cl::desc("Alias for --disassemble-all"),
cl::aliasopt(DisassembleAll));
2011-01-20 14:39:06 +08:00
cl::opt<bool>
llvm::Relocations("r", cl::desc("Display the relocation entries in the file"));
cl::opt<bool>
llvm::SectionContents("s", cl::desc("Display the content of each section"));
cl::opt<bool>
llvm::SymbolTable("t", cl::desc("Display the symbol table"));
cl::opt<bool>
llvm::ExportsTrie("exports-trie", cl::desc("Display mach-o exported symbols"));
cl::opt<bool>
llvm::Rebase("rebase", cl::desc("Display mach-o rebasing info"));
cl::opt<bool>
llvm::Bind("bind", cl::desc("Display mach-o binding info"));
cl::opt<bool>
llvm::LazyBind("lazy-bind", cl::desc("Display mach-o lazy binding info"));
cl::opt<bool>
llvm::WeakBind("weak-bind", cl::desc("Display mach-o weak binding info"));
cl::opt<bool>
llvm::RawClangAST("raw-clang-ast",
cl::desc("Dump the raw binary contents of the clang AST section"));
static cl::opt<bool>
MachOOpt("macho", cl::desc("Use MachO specific object file parser"));
static cl::alias
MachOm("m", cl::desc("Alias for --macho"), cl::aliasopt(MachOOpt));
cl::opt<std::string>
llvm::TripleName("triple", cl::desc("Target triple to disassemble for, "
"see -version for available targets"));
2011-01-20 14:39:06 +08:00
cl::opt<std::string>
llvm::MCPU("mcpu",
cl::desc("Target a specific cpu type (-mcpu=help for details)"),
cl::value_desc("cpu-name"),
cl::init(""));
cl::opt<std::string>
llvm::ArchName("arch-name", cl::desc("Target arch to disassemble for, "
"see -version for available targets"));
2011-01-20 14:39:06 +08:00
cl::opt<bool>
llvm::SectionHeaders("section-headers", cl::desc("Display summaries of the "
"headers for each section."));
static cl::alias
SectionHeadersShort("headers", cl::desc("Alias for --section-headers"),
cl::aliasopt(SectionHeaders));
static cl::alias
SectionHeadersShorter("h", cl::desc("Alias for --section-headers"),
cl::aliasopt(SectionHeaders));
cl::list<std::string>
llvm::FilterSections("section", cl::desc("Operate on the specified sections only. "
"With -macho dump segment,section"));
cl::alias
static FilterSectionsj("j", cl::desc("Alias for --section"),
cl::aliasopt(llvm::FilterSections));
cl::list<std::string>
llvm::MAttrs("mattr",
cl::CommaSeparated,
cl::desc("Target specific attributes"),
cl::value_desc("a1,+a2,-a3,..."));
cl::opt<bool>
llvm::NoShowRawInsn("no-show-raw-insn", cl::desc("When disassembling "
"instructions, do not print "
"the instruction bytes."));
cl::opt<bool>
llvm::UnwindInfo("unwind-info", cl::desc("Display unwind information"));
static cl::alias
UnwindInfoShort("u", cl::desc("Alias for --unwind-info"),
cl::aliasopt(UnwindInfo));
cl::opt<bool>
llvm::PrivateHeaders("private-headers",
cl::desc("Display format specific file headers"));
cl::opt<bool>
llvm::FirstPrivateHeader("private-header",
cl::desc("Display only the first format specific file "
"header"));
static cl::alias
PrivateHeadersShort("p", cl::desc("Alias for --private-headers"),
cl::aliasopt(PrivateHeaders));
cl::opt<bool>
llvm::PrintImmHex("print-imm-hex",
cl::desc("Use hex format for immediate values"));
cl::opt<bool> PrintFaultMaps("fault-map-section",
cl::desc("Display contents of faultmap section"));
cl::opt<DIDumpType> llvm::DwarfDumpType(
"dwarf", cl::init(DIDT_Null), cl::desc("Dump of dwarf debug sections:"),
cl::values(clEnumValN(DIDT_Frames, "frames", ".debug_frame")));
cl::opt<bool> PrintSource(
"source",
cl::desc(
"Display source inlined with disassembly. Implies disassmble object"));
cl::alias PrintSourceShort("S", cl::desc("Alias for -source"),
cl::aliasopt(PrintSource));
cl::opt<bool> PrintLines("line-numbers",
cl::desc("Display source line numbers with "
"disassembly. Implies disassemble object"));
cl::alias PrintLinesShort("l", cl::desc("Alias for -line-numbers"),
cl::aliasopt(PrintLines));
cl::opt<unsigned long long>
StartAddress("start-address", cl::desc("Disassemble beginning at address"),
cl::value_desc("address"), cl::init(0));
cl::opt<unsigned long long>
StopAddress("stop-address", cl::desc("Stop disassembly at address"),
cl::value_desc("address"), cl::init(UINT64_MAX));
static StringRef ToolName;
namespace {
typedef std::function<bool(llvm::object::SectionRef const &)> FilterPredicate;
class SectionFilterIterator {
public:
SectionFilterIterator(FilterPredicate P,
llvm::object::section_iterator const &I,
llvm::object::section_iterator const &E)
: Predicate(std::move(P)), Iterator(I), End(E) {
ScanPredicate();
}
const llvm::object::SectionRef &operator*() const { return *Iterator; }
SectionFilterIterator &operator++() {
++Iterator;
ScanPredicate();
return *this;
}
bool operator!=(SectionFilterIterator const &Other) const {
return Iterator != Other.Iterator;
}
private:
void ScanPredicate() {
while (Iterator != End && !Predicate(*Iterator)) {
++Iterator;
}
}
FilterPredicate Predicate;
llvm::object::section_iterator Iterator;
llvm::object::section_iterator End;
};
class SectionFilter {
public:
SectionFilter(FilterPredicate P, llvm::object::ObjectFile const &O)
: Predicate(std::move(P)), Object(O) {}
SectionFilterIterator begin() {
return SectionFilterIterator(Predicate, Object.section_begin(),
Object.section_end());
}
SectionFilterIterator end() {
return SectionFilterIterator(Predicate, Object.section_end(),
Object.section_end());
}
private:
FilterPredicate Predicate;
llvm::object::ObjectFile const &Object;
};
SectionFilter ToolSectionFilter(llvm::object::ObjectFile const &O) {
return SectionFilter(
[](llvm::object::SectionRef const &S) {
if (FilterSections.empty())
return true;
llvm::StringRef String;
std::error_code error = S.getName(String);
if (error)
return false;
return is_contained(FilterSections, String);
},
O);
}
}
void llvm::error(std::error_code EC) {
if (!EC)
return;
errs() << ToolName << ": error reading file: " << EC.message() << ".\n";
errs().flush();
exit(1);
2011-01-20 14:39:06 +08:00
}
LLVM_ATTRIBUTE_NORETURN void llvm::error(Twine Message) {
errs() << ToolName << ": " << Message << ".\n";
errs().flush();
exit(1);
}
LLVM_ATTRIBUTE_NORETURN void llvm::report_error(StringRef File,
Twine Message) {
errs() << ToolName << ": '" << File << "': " << Message << ".\n";
exit(1);
}
LLVM_ATTRIBUTE_NORETURN void llvm::report_error(StringRef File,
std::error_code EC) {
assert(EC);
errs() << ToolName << ": '" << File << "': " << EC.message() << ".\n";
exit(1);
}
Thread Expected<...> up from createMachOObjectFile() to allow llvm-objdump to produce a real error message Produce the first specific error message for a malformed Mach-O file describing the problem instead of the generic message for object_error::parse_failed of "Invalid data was encountered while parsing the file”.  Many more good error messages will follow after this first one. This is built on Lang Hames’ great work of adding the ’Error' class for structured error handling and threading Error through MachOObjectFile construction. And making createMachOObjectFile return Expected<...> . So to to get the error to the llvm-obdump tool, I changed the stack of these methods to also return Expected<...> : object::ObjectFile::createObjectFile() object::SymbolicFile::createSymbolicFile() object::createBinary() Then finally in ParseInputMachO() in MachODump.cpp the error can be reported and the specific error message can be printed in llvm-objdump and can be seen in the existing test case for the existing malformed binary but with the updated error message. Converting these interfaces to Expected<> from ErrorOr<> does involve touching a number of places. To contain the changes for now use of errorToErrorCode() and errorOrToExpected() are used where the callers are yet to be converted. 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(ObjOrErr.takeError()) so the buggy code will not crash since needed to deal with the Error. Note there is one fix also needed to lld/COFF/InputFiles.cpp 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: 265606
2016-04-07 06:14:09 +08:00
LLVM_ATTRIBUTE_NORETURN void llvm::report_error(StringRef File,
llvm::Error E) {
assert(E);
std::string Buf;
raw_string_ostream OS(Buf);
logAllUnhandledErrors(std::move(E), OS, "");
OS.flush();
errs() << ToolName << ": '" << File << "': " << Buf;
Thread Expected<...> up from createMachOObjectFile() to allow llvm-objdump to produce a real error message Produce the first specific error message for a malformed Mach-O file describing the problem instead of the generic message for object_error::parse_failed of "Invalid data was encountered while parsing the file”.  Many more good error messages will follow after this first one. This is built on Lang Hames’ great work of adding the ’Error' class for structured error handling and threading Error through MachOObjectFile construction. And making createMachOObjectFile return Expected<...> . So to to get the error to the llvm-obdump tool, I changed the stack of these methods to also return Expected<...> : object::ObjectFile::createObjectFile() object::SymbolicFile::createSymbolicFile() object::createBinary() Then finally in ParseInputMachO() in MachODump.cpp the error can be reported and the specific error message can be printed in llvm-objdump and can be seen in the existing test case for the existing malformed binary but with the updated error message. Converting these interfaces to Expected<> from ErrorOr<> does involve touching a number of places. To contain the changes for now use of errorToErrorCode() and errorOrToExpected() are used where the callers are yet to be converted. 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(ObjOrErr.takeError()) so the buggy code will not crash since needed to deal with the Error. Note there is one fix also needed to lld/COFF/InputFiles.cpp 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: 265606
2016-04-07 06:14:09 +08:00
exit(1);
}
LLVM_ATTRIBUTE_NORETURN void llvm::report_error(StringRef ArchiveName,
StringRef FileName,
llvm::Error E,
StringRef ArchitectureName) {
assert(E);
errs() << ToolName << ": ";
if (ArchiveName != "")
errs() << ArchiveName << "(" << FileName << ")";
else
errs() << "'" << FileName << "'";
if (!ArchitectureName.empty())
errs() << " (for architecture " << ArchitectureName << ")";
std::string Buf;
raw_string_ostream OS(Buf);
logAllUnhandledErrors(std::move(E), OS, "");
OS.flush();
errs() << ": " << Buf;
exit(1);
}
LLVM_ATTRIBUTE_NORETURN void llvm::report_error(StringRef ArchiveName,
const object::Archive::Child &C,
llvm::Error E,
StringRef ArchitectureName) {
Expected<StringRef> NameOrErr = C.getName();
// TODO: if we have a error getting the name then it would be nice to print
// the index of which archive member this is and or its offset in the
// archive instead of "???" as the name.
if (!NameOrErr) {
consumeError(NameOrErr.takeError());
llvm::report_error(ArchiveName, "???", std::move(E), ArchitectureName);
} else
llvm::report_error(ArchiveName, NameOrErr.get(), std::move(E),
ArchitectureName);
}
static const Target *getTarget(const ObjectFile *Obj = nullptr) {
2011-01-20 14:39:06 +08:00
// Figure out the target triple.
llvm::Triple TheTriple("unknown-unknown-unknown");
2011-01-20 15:22:04 +08:00
if (TripleName.empty()) {
Add MCSymbolizer for symbolic/annotated disassembly. This is a basic first step towards symbolization of disassembled instructions. This used to be done using externally provided (C API) callbacks. This patch introduces: - the MCSymbolizer class, that mimics the same functions that were used in the X86 and ARM disassemblers to symbolize immediate operands and to annotate loads based off PC (for things like c string literals). - the MCExternalSymbolizer class, which implements the old C API. - the MCRelocationInfo class, which provides a way for targets to translate relocations (either object::RelocationRef, or disassembler C API VariantKinds) to MCExprs. - the MCObjectSymbolizer class, which does symbolization using what it finds in an object::ObjectFile. This makes simple symbolization (with no fancy relocation stuff) work for all object formats! - x86-64 Mach-O and ELF MCRelocationInfos. - A basic ARM Mach-O MCRelocationInfo, that provides just enough to support the C API VariantKinds. Most of what works in otool (the only user of the old symbolization API that I know of) for x86-64 symbolic disassembly (-tvV) works, namely: - symbol references: call _foo; jmp 15 <_foo+50> - relocations: call _foo-_bar; call _foo-4 - __cf?string: leaq 193(%rip), %rax ## literal pool for "hello" Stub support is the main missing part (because libObject doesn't know, among other things, about mach-o indirect symbols). As for the MCSymbolizer API, instead of relying on the disassemblers to call the tryAdding* methods, maybe this could be done automagically using InstrInfo? For instance, even though PC-relative LEAs are used to get the address of string literals in a typical Mach-O file, a MOV would be used in an ELF file. And right now, the explicit symbolization only recognizes PC-relative LEAs. InstrInfo should have already have most of what is needed to know what to symbolize, so this can definitely be improved. I'd also like to remove object::RelocationRef::getValueString (it seems only used by relocation printing in objdump), as simply printing the created MCExpr is definitely enough (and cleaner than string concats). llvm-svn: 182625
2013-05-24 08:39:57 +08:00
if (Obj) {
TheTriple.setArch(Triple::ArchType(Obj->getArch()));
Add MCSymbolizer for symbolic/annotated disassembly. This is a basic first step towards symbolization of disassembled instructions. This used to be done using externally provided (C API) callbacks. This patch introduces: - the MCSymbolizer class, that mimics the same functions that were used in the X86 and ARM disassemblers to symbolize immediate operands and to annotate loads based off PC (for things like c string literals). - the MCExternalSymbolizer class, which implements the old C API. - the MCRelocationInfo class, which provides a way for targets to translate relocations (either object::RelocationRef, or disassembler C API VariantKinds) to MCExprs. - the MCObjectSymbolizer class, which does symbolization using what it finds in an object::ObjectFile. This makes simple symbolization (with no fancy relocation stuff) work for all object formats! - x86-64 Mach-O and ELF MCRelocationInfos. - A basic ARM Mach-O MCRelocationInfo, that provides just enough to support the C API VariantKinds. Most of what works in otool (the only user of the old symbolization API that I know of) for x86-64 symbolic disassembly (-tvV) works, namely: - symbol references: call _foo; jmp 15 <_foo+50> - relocations: call _foo-_bar; call _foo-4 - __cf?string: leaq 193(%rip), %rax ## literal pool for "hello" Stub support is the main missing part (because libObject doesn't know, among other things, about mach-o indirect symbols). As for the MCSymbolizer API, instead of relying on the disassemblers to call the tryAdding* methods, maybe this could be done automagically using InstrInfo? For instance, even though PC-relative LEAs are used to get the address of string literals in a typical Mach-O file, a MOV would be used in an ELF file. And right now, the explicit symbolization only recognizes PC-relative LEAs. InstrInfo should have already have most of what is needed to know what to symbolize, so this can definitely be improved. I'd also like to remove object::RelocationRef::getValueString (it seems only used by relocation printing in objdump), as simply printing the created MCExpr is definitely enough (and cleaner than string concats). llvm-svn: 182625
2013-05-24 08:39:57 +08:00
// TheTriple defaults to ELF, and COFF doesn't have an environment:
// the best we can do here is indicate that it is mach-o.
if (Obj->isMachO())
TheTriple.setObjectFormat(Triple::MachO);
if (Obj->isCOFF()) {
const auto COFFObj = dyn_cast<COFFObjectFile>(Obj);
if (COFFObj->getArch() == Triple::thumb)
TheTriple.setTriple("thumbv7-windows");
}
Add MCSymbolizer for symbolic/annotated disassembly. This is a basic first step towards symbolization of disassembled instructions. This used to be done using externally provided (C API) callbacks. This patch introduces: - the MCSymbolizer class, that mimics the same functions that were used in the X86 and ARM disassemblers to symbolize immediate operands and to annotate loads based off PC (for things like c string literals). - the MCExternalSymbolizer class, which implements the old C API. - the MCRelocationInfo class, which provides a way for targets to translate relocations (either object::RelocationRef, or disassembler C API VariantKinds) to MCExprs. - the MCObjectSymbolizer class, which does symbolization using what it finds in an object::ObjectFile. This makes simple symbolization (with no fancy relocation stuff) work for all object formats! - x86-64 Mach-O and ELF MCRelocationInfos. - A basic ARM Mach-O MCRelocationInfo, that provides just enough to support the C API VariantKinds. Most of what works in otool (the only user of the old symbolization API that I know of) for x86-64 symbolic disassembly (-tvV) works, namely: - symbol references: call _foo; jmp 15 <_foo+50> - relocations: call _foo-_bar; call _foo-4 - __cf?string: leaq 193(%rip), %rax ## literal pool for "hello" Stub support is the main missing part (because libObject doesn't know, among other things, about mach-o indirect symbols). As for the MCSymbolizer API, instead of relying on the disassemblers to call the tryAdding* methods, maybe this could be done automagically using InstrInfo? For instance, even though PC-relative LEAs are used to get the address of string literals in a typical Mach-O file, a MOV would be used in an ELF file. And right now, the explicit symbolization only recognizes PC-relative LEAs. InstrInfo should have already have most of what is needed to know what to symbolize, so this can definitely be improved. I'd also like to remove object::RelocationRef::getValueString (it seems only used by relocation printing in objdump), as simply printing the created MCExpr is definitely enough (and cleaner than string concats). llvm-svn: 182625
2013-05-24 08:39:57 +08:00
}
2011-01-20 15:22:04 +08:00
} else
TheTriple.setTriple(Triple::normalize(TripleName));
2011-01-20 14:39:06 +08:00
// Get the target specific parser.
std::string Error;
const Target *TheTarget = TargetRegistry::lookupTarget(ArchName, TheTriple,
Error);
if (!TheTarget) {
if (Obj)
report_error(Obj->getFileName(), "can't find target: " + Error);
else
error("can't find target: " + Error);
}
// Update the triple name and return the found target.
TripleName = TheTriple.getTriple();
return TheTarget;
2011-01-20 14:39:06 +08:00
}
bool llvm::RelocAddressLess(RelocationRef a, RelocationRef b) {
2015-07-06 23:47:43 +08:00
return a.getOffset() < b.getOffset();
}
namespace {
class SourcePrinter {
protected:
DILineInfo OldLineInfo;
const ObjectFile *Obj;
std::unique_ptr<symbolize::LLVMSymbolizer> Symbolizer;
// File name to file contents of source
std::unordered_map<std::string, std::unique_ptr<MemoryBuffer>> SourceCache;
// Mark the line endings of the cached source
std::unordered_map<std::string, std::vector<StringRef>> LineCache;
private:
bool cacheSource(std::string File);
public:
virtual ~SourcePrinter() {}
SourcePrinter() : Obj(nullptr), Symbolizer(nullptr) {}
SourcePrinter(const ObjectFile *Obj, StringRef DefaultArch) : Obj(Obj) {
symbolize::LLVMSymbolizer::Options SymbolizerOpts(
DILineInfoSpecifier::FunctionNameKind::None, true, false, false,
DefaultArch);
Symbolizer.reset(new symbolize::LLVMSymbolizer(SymbolizerOpts));
}
virtual void printSourceLine(raw_ostream &OS, uint64_t Address,
StringRef Delimiter = "; ");
};
bool SourcePrinter::cacheSource(std::string File) {
auto BufferOrError = MemoryBuffer::getFile(File);
if (!BufferOrError)
return false;
// Chomp the file to get lines
size_t BufferSize = (*BufferOrError)->getBufferSize();
const char *BufferStart = (*BufferOrError)->getBufferStart();
for (const char *Start = BufferStart, *End = BufferStart;
End < BufferStart + BufferSize; End++)
if (*End == '\n' || End == BufferStart + BufferSize - 1 ||
(*End == '\r' && *(End + 1) == '\n')) {
LineCache[File].push_back(StringRef(Start, End - Start));
if (*End == '\r')
End++;
Start = End + 1;
}
SourceCache[File] = std::move(*BufferOrError);
return true;
}
void SourcePrinter::printSourceLine(raw_ostream &OS, uint64_t Address,
StringRef Delimiter) {
if (!Symbolizer)
return;
DILineInfo LineInfo = DILineInfo();
auto ExpectecLineInfo =
Symbolizer->symbolizeCode(Obj->getFileName(), Address);
if (!ExpectecLineInfo)
consumeError(ExpectecLineInfo.takeError());
else
LineInfo = *ExpectecLineInfo;
if ((LineInfo.FileName == "<invalid>") || OldLineInfo.Line == LineInfo.Line ||
LineInfo.Line == 0)
return;
if (PrintLines)
OS << Delimiter << LineInfo.FileName << ":" << LineInfo.Line << "\n";
if (PrintSource) {
if (SourceCache.find(LineInfo.FileName) == SourceCache.end())
if (!cacheSource(LineInfo.FileName))
return;
auto FileBuffer = SourceCache.find(LineInfo.FileName);
if (FileBuffer != SourceCache.end()) {
auto LineBuffer = LineCache.find(LineInfo.FileName);
if (LineBuffer != LineCache.end())
// Vector begins at 0, line numbers are non-zero
OS << Delimiter << LineBuffer->second[LineInfo.Line - 1].ltrim()
<< "\n";
}
}
OldLineInfo = LineInfo;
}
static bool isArmElf(const ObjectFile *Obj) {
return (Obj->isELF() &&
(Obj->getArch() == Triple::aarch64 ||
Obj->getArch() == Triple::aarch64_be ||
Obj->getArch() == Triple::arm || Obj->getArch() == Triple::armeb ||
Obj->getArch() == Triple::thumb ||
Obj->getArch() == Triple::thumbeb));
}
class PrettyPrinter {
public:
virtual ~PrettyPrinter(){}
virtual void printInst(MCInstPrinter &IP, const MCInst *MI,
ArrayRef<uint8_t> Bytes, uint64_t Address,
raw_ostream &OS, StringRef Annot,
MCSubtargetInfo const &STI, SourcePrinter *SP) {
if (SP && (PrintSource || PrintLines))
SP->printSourceLine(OS, Address);
OS << format("%8" PRIx64 ":", Address);
if (!NoShowRawInsn) {
OS << "\t";
dumpBytes(Bytes, OS);
}
if (MI)
IP.printInst(MI, OS, "", STI);
else
OS << " <unknown>";
}
};
PrettyPrinter PrettyPrinterInst;
class HexagonPrettyPrinter : public PrettyPrinter {
public:
void printLead(ArrayRef<uint8_t> Bytes, uint64_t Address,
raw_ostream &OS) {
uint32_t opcode =
(Bytes[3] << 24) | (Bytes[2] << 16) | (Bytes[1] << 8) | Bytes[0];
OS << format("%8" PRIx64 ":", Address);
if (!NoShowRawInsn) {
OS << "\t";
dumpBytes(Bytes.slice(0, 4), OS);
OS << format("%08" PRIx32, opcode);
}
}
void printInst(MCInstPrinter &IP, const MCInst *MI, ArrayRef<uint8_t> Bytes,
uint64_t Address, raw_ostream &OS, StringRef Annot,
MCSubtargetInfo const &STI, SourcePrinter *SP) override {
if (SP && (PrintSource || PrintLines))
SP->printSourceLine(OS, Address, "");
if (!MI) {
printLead(Bytes, Address, OS);
OS << " <unknown>";
return;
}
std::string Buffer;
{
raw_string_ostream TempStream(Buffer);
IP.printInst(MI, TempStream, "", STI);
}
StringRef Contents(Buffer);
// Split off bundle attributes
auto PacketBundle = Contents.rsplit('\n');
// Split off first instruction from the rest
auto HeadTail = PacketBundle.first.split('\n');
auto Preamble = " { ";
auto Separator = "";
while(!HeadTail.first.empty()) {
OS << Separator;
Separator = "\n";
if (SP && (PrintSource || PrintLines))
SP->printSourceLine(OS, Address, "");
printLead(Bytes, Address, OS);
OS << Preamble;
Preamble = " ";
StringRef Inst;
auto Duplex = HeadTail.first.split('\v');
if(!Duplex.second.empty()){
OS << Duplex.first;
OS << "; ";
Inst = Duplex.second;
}
else
Inst = HeadTail.first;
OS << Inst;
Bytes = Bytes.slice(4);
Address += 4;
HeadTail = HeadTail.second.split('\n');
}
OS << " } " << PacketBundle.second;
}
};
HexagonPrettyPrinter HexagonPrettyPrinterInst;
class AMDGCNPrettyPrinter : public PrettyPrinter {
public:
void printInst(MCInstPrinter &IP, const MCInst *MI, ArrayRef<uint8_t> Bytes,
uint64_t Address, raw_ostream &OS, StringRef Annot,
MCSubtargetInfo const &STI, SourcePrinter *SP) override {
if (!MI) {
OS << " <unknown>";
return;
}
SmallString<40> InstStr;
raw_svector_ostream IS(InstStr);
IP.printInst(MI, IS, "", STI);
OS << left_justify(IS.str(), 60) << format("// %012" PRIX64 ": ", Address);
typedef support::ulittle32_t U32;
for (auto D : makeArrayRef(reinterpret_cast<const U32*>(Bytes.data()),
Bytes.size() / sizeof(U32)))
// D should be explicitly casted to uint32_t here as it is passed
// by format to snprintf as vararg.
OS << format("%08" PRIX32 " ", static_cast<uint32_t>(D));
if (!Annot.empty())
OS << "// " << Annot;
}
};
AMDGCNPrettyPrinter AMDGCNPrettyPrinterInst;
PrettyPrinter &selectPrettyPrinter(Triple const &Triple) {
switch(Triple.getArch()) {
default:
return PrettyPrinterInst;
case Triple::hexagon:
return HexagonPrettyPrinterInst;
case Triple::amdgcn:
return AMDGCNPrettyPrinterInst;
}
}
}
template <class ELFT>
static std::error_code getRelocationValueString(const ELFObjectFile<ELFT> *Obj,
const RelocationRef &RelRef,
SmallVectorImpl<char> &Result) {
DataRefImpl Rel = RelRef.getRawDataRefImpl();
typedef typename ELFObjectFile<ELFT>::Elf_Sym Elf_Sym;
typedef typename ELFObjectFile<ELFT>::Elf_Shdr Elf_Shdr;
typedef typename ELFObjectFile<ELFT>::Elf_Rela Elf_Rela;
const ELFFile<ELFT> &EF = *Obj->getELFFile();
auto SecOrErr = EF.getSection(Rel.d.a);
if (!SecOrErr)
return errorToErrorCode(SecOrErr.takeError());
const Elf_Shdr *Sec = *SecOrErr;
auto SymTabOrErr = EF.getSection(Sec->sh_link);
if (!SymTabOrErr)
return errorToErrorCode(SymTabOrErr.takeError());
const Elf_Shdr *SymTab = *SymTabOrErr;
assert(SymTab->sh_type == ELF::SHT_SYMTAB ||
SymTab->sh_type == ELF::SHT_DYNSYM);
auto StrTabSec = EF.getSection(SymTab->sh_link);
if (!StrTabSec)
return errorToErrorCode(StrTabSec.takeError());
auto StrTabOrErr = EF.getStringTable(*StrTabSec);
if (!StrTabOrErr)
return errorToErrorCode(StrTabOrErr.takeError());
StringRef StrTab = *StrTabOrErr;
uint8_t type = RelRef.getType();
StringRef res;
int64_t addend = 0;
switch (Sec->sh_type) {
default:
return object_error::parse_failed;
case ELF::SHT_REL: {
// TODO: Read implicit addend from section data.
break;
}
case ELF::SHT_RELA: {
const Elf_Rela *ERela = Obj->getRela(Rel);
addend = ERela->r_addend;
break;
}
}
symbol_iterator SI = RelRef.getSymbol();
const Elf_Sym *symb = Obj->getSymbol(SI->getRawDataRefImpl());
StringRef Target;
if (symb->getType() == ELF::STT_SECTION) {
Expected<section_iterator> SymSI = SI->getSection();
if (!SymSI)
return errorToErrorCode(SymSI.takeError());
const Elf_Shdr *SymSec = Obj->getSection((*SymSI)->getRawDataRefImpl());
auto SecName = EF.getSectionName(SymSec);
if (!SecName)
return errorToErrorCode(SecName.takeError());
Target = *SecName;
} else {
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
2016-04-21 05:24:34 +08:00
Expected<StringRef> SymName = symb->getName(StrTab);
if (!SymName)
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
2016-04-21 05:24:34 +08:00
return errorToErrorCode(SymName.takeError());
Target = *SymName;
}
switch (EF.getHeader()->e_machine) {
case ELF::EM_X86_64:
switch (type) {
case ELF::R_X86_64_PC8:
case ELF::R_X86_64_PC16:
case ELF::R_X86_64_PC32: {
std::string fmtbuf;
raw_string_ostream fmt(fmtbuf);
fmt << Target << (addend < 0 ? "" : "+") << addend << "-P";
fmt.flush();
Result.append(fmtbuf.begin(), fmtbuf.end());
} break;
case ELF::R_X86_64_8:
case ELF::R_X86_64_16:
case ELF::R_X86_64_32:
case ELF::R_X86_64_32S:
case ELF::R_X86_64_64: {
std::string fmtbuf;
raw_string_ostream fmt(fmtbuf);
fmt << Target << (addend < 0 ? "" : "+") << addend;
fmt.flush();
Result.append(fmtbuf.begin(), fmtbuf.end());
} break;
default:
res = "Unknown";
}
break;
case ELF::EM_LANAI:
case ELF::EM_AVR:
case ELF::EM_AARCH64: {
std::string fmtbuf;
raw_string_ostream fmt(fmtbuf);
fmt << Target;
if (addend != 0)
fmt << (addend < 0 ? "" : "+") << addend;
fmt.flush();
Result.append(fmtbuf.begin(), fmtbuf.end());
break;
}
case ELF::EM_386:
case ELF::EM_IAMCU:
case ELF::EM_ARM:
case ELF::EM_HEXAGON:
case ELF::EM_MIPS:
case ELF::EM_BPF:
case ELF::EM_RISCV:
res = Target;
break;
case ELF::EM_WEBASSEMBLY:
switch (type) {
case ELF::R_WEBASSEMBLY_DATA: {
std::string fmtbuf;
raw_string_ostream fmt(fmtbuf);
fmt << Target << (addend < 0 ? "" : "+") << addend;
fmt.flush();
Result.append(fmtbuf.begin(), fmtbuf.end());
break;
}
case ELF::R_WEBASSEMBLY_FUNCTION:
res = Target;
break;
default:
res = "Unknown";
}
break;
default:
res = "Unknown";
}
if (Result.empty())
Result.append(res.begin(), res.end());
return std::error_code();
}
static std::error_code getRelocationValueString(const ELFObjectFileBase *Obj,
const RelocationRef &Rel,
SmallVectorImpl<char> &Result) {
if (auto *ELF32LE = dyn_cast<ELF32LEObjectFile>(Obj))
return getRelocationValueString(ELF32LE, Rel, Result);
if (auto *ELF64LE = dyn_cast<ELF64LEObjectFile>(Obj))
return getRelocationValueString(ELF64LE, Rel, Result);
if (auto *ELF32BE = dyn_cast<ELF32BEObjectFile>(Obj))
return getRelocationValueString(ELF32BE, Rel, Result);
auto *ELF64BE = cast<ELF64BEObjectFile>(Obj);
return getRelocationValueString(ELF64BE, Rel, Result);
}
static std::error_code getRelocationValueString(const COFFObjectFile *Obj,
const RelocationRef &Rel,
SmallVectorImpl<char> &Result) {
symbol_iterator SymI = Rel.getSymbol();
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
2016-04-21 05:24:34 +08:00
Expected<StringRef> SymNameOrErr = SymI->getName();
if (!SymNameOrErr)
return errorToErrorCode(SymNameOrErr.takeError());
StringRef SymName = *SymNameOrErr;
Result.append(SymName.begin(), SymName.end());
return std::error_code();
}
static void printRelocationTargetName(const MachOObjectFile *O,
const MachO::any_relocation_info &RE,
raw_string_ostream &fmt) {
bool IsScattered = O->isRelocationScattered(RE);
// Target of a scattered relocation is an address. In the interest of
// generating pretty output, scan through the symbol table looking for a
// symbol that aligns with that address. If we find one, print it.
// Otherwise, we just print the hex address of the target.
if (IsScattered) {
uint32_t Val = O->getPlainRelocationSymbolNum(RE);
for (const SymbolRef &Symbol : O->symbols()) {
std::error_code ec;
Expected<uint64_t> Addr = Symbol.getAddress();
if (!Addr)
report_error(O->getFileName(), Addr.takeError());
if (*Addr != Val)
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
2016-04-21 05:24:34 +08:00
Expected<StringRef> Name = Symbol.getName();
if (!Name)
report_error(O->getFileName(), Name.takeError());
fmt << *Name;
return;
}
// If we couldn't find a symbol that this relocation refers to, try
// to find a section beginning instead.
for (const SectionRef &Section : ToolSectionFilter(*O)) {
std::error_code ec;
StringRef Name;
uint64_t Addr = Section.getAddress();
if (Addr != Val)
continue;
if ((ec = Section.getName(Name)))
report_error(O->getFileName(), ec);
fmt << Name;
return;
}
fmt << format("0x%x", Val);
return;
}
StringRef S;
bool isExtern = O->getPlainRelocationExternal(RE);
uint64_t Val = O->getPlainRelocationSymbolNum(RE);
if (isExtern) {
symbol_iterator SI = O->symbol_begin();
advance(SI, Val);
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
2016-04-21 05:24:34 +08:00
Expected<StringRef> SOrErr = SI->getName();
if (!SOrErr)
report_error(O->getFileName(), SOrErr.takeError());
S = *SOrErr;
} else {
section_iterator SI = O->section_begin();
// Adjust for the fact that sections are 1-indexed.
advance(SI, Val - 1);
SI->getName(S);
}
fmt << S;
}
static std::error_code getRelocationValueString(const MachOObjectFile *Obj,
const RelocationRef &RelRef,
SmallVectorImpl<char> &Result) {
DataRefImpl Rel = RelRef.getRawDataRefImpl();
MachO::any_relocation_info RE = Obj->getRelocation(Rel);
unsigned Arch = Obj->getArch();
std::string fmtbuf;
raw_string_ostream fmt(fmtbuf);
unsigned Type = Obj->getAnyRelocationType(RE);
bool IsPCRel = Obj->getAnyRelocationPCRel(RE);
// Determine any addends that should be displayed with the relocation.
// These require decoding the relocation type, which is triple-specific.
// X86_64 has entirely custom relocation types.
if (Arch == Triple::x86_64) {
bool isPCRel = Obj->getAnyRelocationPCRel(RE);
switch (Type) {
case MachO::X86_64_RELOC_GOT_LOAD:
case MachO::X86_64_RELOC_GOT: {
printRelocationTargetName(Obj, RE, fmt);
fmt << "@GOT";
if (isPCRel)
fmt << "PCREL";
break;
}
case MachO::X86_64_RELOC_SUBTRACTOR: {
DataRefImpl RelNext = Rel;
Obj->moveRelocationNext(RelNext);
MachO::any_relocation_info RENext = Obj->getRelocation(RelNext);
// X86_64_RELOC_SUBTRACTOR must be followed by a relocation of type
// X86_64_RELOC_UNSIGNED.
// NOTE: Scattered relocations don't exist on x86_64.
unsigned RType = Obj->getAnyRelocationType(RENext);
if (RType != MachO::X86_64_RELOC_UNSIGNED)
report_error(Obj->getFileName(), "Expected X86_64_RELOC_UNSIGNED after "
"X86_64_RELOC_SUBTRACTOR.");
// The X86_64_RELOC_UNSIGNED contains the minuend symbol;
// X86_64_RELOC_SUBTRACTOR contains the subtrahend.
printRelocationTargetName(Obj, RENext, fmt);
fmt << "-";
printRelocationTargetName(Obj, RE, fmt);
break;
}
case MachO::X86_64_RELOC_TLV:
printRelocationTargetName(Obj, RE, fmt);
fmt << "@TLV";
if (isPCRel)
fmt << "P";
break;
case MachO::X86_64_RELOC_SIGNED_1:
printRelocationTargetName(Obj, RE, fmt);
fmt << "-1";
break;
case MachO::X86_64_RELOC_SIGNED_2:
printRelocationTargetName(Obj, RE, fmt);
fmt << "-2";
break;
case MachO::X86_64_RELOC_SIGNED_4:
printRelocationTargetName(Obj, RE, fmt);
fmt << "-4";
break;
default:
printRelocationTargetName(Obj, RE, fmt);
break;
}
// X86 and ARM share some relocation types in common.
} else if (Arch == Triple::x86 || Arch == Triple::arm ||
Arch == Triple::ppc) {
// Generic relocation types...
switch (Type) {
case MachO::GENERIC_RELOC_PAIR: // prints no info
return std::error_code();
case MachO::GENERIC_RELOC_SECTDIFF: {
DataRefImpl RelNext = Rel;
Obj->moveRelocationNext(RelNext);
MachO::any_relocation_info RENext = Obj->getRelocation(RelNext);
// X86 sect diff's must be followed by a relocation of type
// GENERIC_RELOC_PAIR.
unsigned RType = Obj->getAnyRelocationType(RENext);
if (RType != MachO::GENERIC_RELOC_PAIR)
report_error(Obj->getFileName(), "Expected GENERIC_RELOC_PAIR after "
"GENERIC_RELOC_SECTDIFF.");
printRelocationTargetName(Obj, RE, fmt);
fmt << "-";
printRelocationTargetName(Obj, RENext, fmt);
break;
}
}
if (Arch == Triple::x86 || Arch == Triple::ppc) {
switch (Type) {
case MachO::GENERIC_RELOC_LOCAL_SECTDIFF: {
DataRefImpl RelNext = Rel;
Obj->moveRelocationNext(RelNext);
MachO::any_relocation_info RENext = Obj->getRelocation(RelNext);
// X86 sect diff's must be followed by a relocation of type
// GENERIC_RELOC_PAIR.
unsigned RType = Obj->getAnyRelocationType(RENext);
if (RType != MachO::GENERIC_RELOC_PAIR)
report_error(Obj->getFileName(), "Expected GENERIC_RELOC_PAIR after "
"GENERIC_RELOC_LOCAL_SECTDIFF.");
printRelocationTargetName(Obj, RE, fmt);
fmt << "-";
printRelocationTargetName(Obj, RENext, fmt);
break;
}
case MachO::GENERIC_RELOC_TLV: {
printRelocationTargetName(Obj, RE, fmt);
fmt << "@TLV";
if (IsPCRel)
fmt << "P";
break;
}
default:
printRelocationTargetName(Obj, RE, fmt);
}
} else { // ARM-specific relocations
switch (Type) {
case MachO::ARM_RELOC_HALF:
case MachO::ARM_RELOC_HALF_SECTDIFF: {
// Half relocations steal a bit from the length field to encode
// whether this is an upper16 or a lower16 relocation.
bool isUpper = Obj->getAnyRelocationLength(RE) >> 1;
if (isUpper)
fmt << ":upper16:(";
else
fmt << ":lower16:(";
printRelocationTargetName(Obj, RE, fmt);
DataRefImpl RelNext = Rel;
Obj->moveRelocationNext(RelNext);
MachO::any_relocation_info RENext = Obj->getRelocation(RelNext);
// ARM half relocs must be followed by a relocation of type
// ARM_RELOC_PAIR.
unsigned RType = Obj->getAnyRelocationType(RENext);
if (RType != MachO::ARM_RELOC_PAIR)
report_error(Obj->getFileName(), "Expected ARM_RELOC_PAIR after "
"ARM_RELOC_HALF");
// NOTE: The half of the target virtual address is stashed in the
// address field of the secondary relocation, but we can't reverse
// engineer the constant offset from it without decoding the movw/movt
// instruction to find the other half in its immediate field.
// ARM_RELOC_HALF_SECTDIFF encodes the second section in the
// symbol/section pointer of the follow-on relocation.
if (Type == MachO::ARM_RELOC_HALF_SECTDIFF) {
fmt << "-";
printRelocationTargetName(Obj, RENext, fmt);
}
fmt << ")";
break;
}
default: { printRelocationTargetName(Obj, RE, fmt); }
}
}
} else
printRelocationTargetName(Obj, RE, fmt);
fmt.flush();
Result.append(fmtbuf.begin(), fmtbuf.end());
return std::error_code();
}
static std::error_code getRelocationValueString(const RelocationRef &Rel,
SmallVectorImpl<char> &Result) {
const ObjectFile *Obj = Rel.getObject();
if (auto *ELF = dyn_cast<ELFObjectFileBase>(Obj))
return getRelocationValueString(ELF, Rel, Result);
if (auto *COFF = dyn_cast<COFFObjectFile>(Obj))
return getRelocationValueString(COFF, Rel, Result);
auto *MachO = cast<MachOObjectFile>(Obj);
return getRelocationValueString(MachO, Rel, Result);
}
/// @brief Indicates whether this relocation should hidden when listing
/// relocations, usually because it is the trailing part of a multipart
/// relocation that will be printed as part of the leading relocation.
static bool getHidden(RelocationRef RelRef) {
const ObjectFile *Obj = RelRef.getObject();
auto *MachO = dyn_cast<MachOObjectFile>(Obj);
if (!MachO)
return false;
unsigned Arch = MachO->getArch();
DataRefImpl Rel = RelRef.getRawDataRefImpl();
uint64_t Type = MachO->getRelocationType(Rel);
// On arches that use the generic relocations, GENERIC_RELOC_PAIR
// is always hidden.
if (Arch == Triple::x86 || Arch == Triple::arm || Arch == Triple::ppc) {
if (Type == MachO::GENERIC_RELOC_PAIR)
return true;
} else if (Arch == Triple::x86_64) {
// On x86_64, X86_64_RELOC_UNSIGNED is hidden only when it follows
// an X86_64_RELOC_SUBTRACTOR.
if (Type == MachO::X86_64_RELOC_UNSIGNED && Rel.d.a > 0) {
DataRefImpl RelPrev = Rel;
RelPrev.d.a--;
uint64_t PrevType = MachO->getRelocationType(RelPrev);
if (PrevType == MachO::X86_64_RELOC_SUBTRACTOR)
return true;
}
}
return false;
}
static uint8_t getElfSymbolType(const ObjectFile *Obj, const SymbolRef &Sym) {
assert(Obj->isELF());
if (auto *Elf32LEObj = dyn_cast<ELF32LEObjectFile>(Obj))
return Elf32LEObj->getSymbol(Sym.getRawDataRefImpl())->getType();
if (auto *Elf64LEObj = dyn_cast<ELF64LEObjectFile>(Obj))
return Elf64LEObj->getSymbol(Sym.getRawDataRefImpl())->getType();
if (auto *Elf32BEObj = dyn_cast<ELF32BEObjectFile>(Obj))
return Elf32BEObj->getSymbol(Sym.getRawDataRefImpl())->getType();
if (auto *Elf64BEObj = cast<ELF64BEObjectFile>(Obj))
return Elf64BEObj->getSymbol(Sym.getRawDataRefImpl())->getType();
llvm_unreachable("Unsupported binary format");
}
static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) {
if (StartAddress > StopAddress)
error("Start address should be less than stop address");
2012-08-08 01:53:14 +08:00
const Target *TheTarget = getTarget(Obj);
2011-01-20 14:39:06 +08:00
// Package up features to be passed to target/subtarget
SubtargetFeatures Features = Obj->getFeatures();
if (MAttrs.size()) {
for (unsigned i = 0; i != MAttrs.size(); ++i)
Features.AddFeature(MAttrs[i]);
}
std::unique_ptr<const MCRegisterInfo> MRI(
TheTarget->createMCRegInfo(TripleName));
if (!MRI)
report_error(Obj->getFileName(), "no register info for target " +
TripleName);
// Set up disassembler.
std::unique_ptr<const MCAsmInfo> AsmInfo(
TheTarget->createMCAsmInfo(*MRI, TripleName));
if (!AsmInfo)
report_error(Obj->getFileName(), "no assembly info for target " +
TripleName);
std::unique_ptr<const MCSubtargetInfo> STI(
TheTarget->createMCSubtargetInfo(TripleName, MCPU, Features.getString()));
if (!STI)
report_error(Obj->getFileName(), "no subtarget info for target " +
TripleName);
std::unique_ptr<const MCInstrInfo> MII(TheTarget->createMCInstrInfo());
if (!MII)
report_error(Obj->getFileName(), "no instruction info for target " +
TripleName);
MCObjectFileInfo MOFI;
MCContext Ctx(AsmInfo.get(), MRI.get(), &MOFI);
// FIXME: for now initialize MCObjectFileInfo with default values
MOFI.InitMCObjectFileInfo(Triple(TripleName), false, CodeModel::Default, Ctx);
std::unique_ptr<MCDisassembler> DisAsm(
TheTarget->createMCDisassembler(*STI, Ctx));
if (!DisAsm)
report_error(Obj->getFileName(), "no disassembler for target " +
TripleName);
std::unique_ptr<const MCInstrAnalysis> MIA(
TheTarget->createMCInstrAnalysis(MII.get()));
MC: Disassembled CFG reconstruction. This patch builds on some existing code to do CFG reconstruction from a disassembled binary: - MCModule represents the binary, and has a list of MCAtoms. - MCAtom represents either disassembled instructions (MCTextAtom), or contiguous data (MCDataAtom), and covers a specific range of addresses. - MCBasicBlock and MCFunction form the reconstructed CFG. An MCBB is backed by an MCTextAtom, and has the usual successors/predecessors. - MCObjectDisassembler creates a module from an ObjectFile using a disassembler. It first builds an atom for each section. It can also construct the CFG, and this splits the text atoms into basic blocks. MCModule and MCAtom were only sketched out; MCFunction and MCBB were implemented under the experimental "-cfg" llvm-objdump -macho option. This cleans them up for further use; llvm-objdump -d -cfg now generates graphviz files for each function found in the binary. In the future, MCObjectDisassembler may be the right place to do "intelligent" disassembly: for example, handling constant islands is just a matter of splitting the atom, using information that may be available in the ObjectFile. Also, better initial atom formation than just using sections is possible using symbols (and things like Mach-O's function_starts load command). This brings two minor regressions in llvm-objdump -macho -cfg: - The printing of a relocation's referenced symbol. - An annotation on loop BBs, i.e., which are their own successor. Relocation printing is replaced by the MCSymbolizer; the basic CFG annotation will be superseded by more related functionality. llvm-svn: 182628
2013-05-24 09:07:04 +08:00
int AsmPrinterVariant = AsmInfo->getAssemblerDialect();
std::unique_ptr<MCInstPrinter> IP(TheTarget->createMCInstPrinter(
Triple(TripleName), AsmPrinterVariant, *AsmInfo, *MII, *MRI));
if (!IP)
report_error(Obj->getFileName(), "no instruction printer for target " +
TripleName);
IP->setPrintImmHex(PrintImmHex);
PrettyPrinter &PIP = selectPrettyPrinter(Triple(TripleName));
StringRef Fmt = Obj->getBytesInAddress() > 4 ? "\t\t%016" PRIx64 ": " :
"\t\t\t%08" PRIx64 ": ";
SourcePrinter SP(Obj, TheTarget->getName());
// Create a mapping, RelocSecs = SectionRelocMap[S], where sections
// in RelocSecs contain the relocations for section S.
std::error_code EC;
std::map<SectionRef, SmallVector<SectionRef, 1>> SectionRelocMap;
for (const SectionRef &Section : ToolSectionFilter(*Obj)) {
section_iterator Sec2 = Section.getRelocatedSection();
if (Sec2 != Obj->section_end())
SectionRelocMap[*Sec2].push_back(Section);
}
// Create a mapping from virtual address to symbol name. This is used to
// pretty print the symbols while disassembling.
typedef std::vector<std::tuple<uint64_t, StringRef, uint8_t>> SectionSymbolsTy;
std::map<SectionRef, SectionSymbolsTy> AllSymbols;
for (const SymbolRef &Symbol : Obj->symbols()) {
Expected<uint64_t> AddressOrErr = Symbol.getAddress();
if (!AddressOrErr)
report_error(Obj->getFileName(), AddressOrErr.takeError());
uint64_t Address = *AddressOrErr;
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
2016-04-21 05:24:34 +08:00
Expected<StringRef> Name = Symbol.getName();
if (!Name)
report_error(Obj->getFileName(), Name.takeError());
if (Name->empty())
continue;
Expected<section_iterator> SectionOrErr = Symbol.getSection();
if (!SectionOrErr)
report_error(Obj->getFileName(), SectionOrErr.takeError());
section_iterator SecI = *SectionOrErr;
if (SecI == Obj->section_end())
continue;
uint8_t SymbolType = ELF::STT_NOTYPE;
if (Obj->isELF())
SymbolType = getElfSymbolType(Obj, Symbol);
AllSymbols[*SecI].emplace_back(Address, *Name, SymbolType);
}
// Create a mapping from virtual address to section.
std::vector<std::pair<uint64_t, SectionRef>> SectionAddresses;
for (SectionRef Sec : Obj->sections())
SectionAddresses.emplace_back(Sec.getAddress(), Sec);
array_pod_sort(SectionAddresses.begin(), SectionAddresses.end());
// Linked executables (.exe and .dll files) typically don't include a real
// symbol table but they might contain an export table.
if (const auto *COFFObj = dyn_cast<COFFObjectFile>(Obj)) {
for (const auto &ExportEntry : COFFObj->export_directories()) {
StringRef Name;
error(ExportEntry.getSymbolName(Name));
if (Name.empty())
continue;
uint32_t RVA;
error(ExportEntry.getExportRVA(RVA));
uint64_t VA = COFFObj->getImageBase() + RVA;
auto Sec = std::upper_bound(
SectionAddresses.begin(), SectionAddresses.end(), VA,
[](uint64_t LHS, const std::pair<uint64_t, SectionRef> &RHS) {
return LHS < RHS.first;
});
if (Sec != SectionAddresses.begin())
--Sec;
else
Sec = SectionAddresses.end();
if (Sec != SectionAddresses.end())
AllSymbols[Sec->second].emplace_back(VA, Name, ELF::STT_NOTYPE);
}
}
// Sort all the symbols, this allows us to use a simple binary search to find
// a symbol near an address.
for (std::pair<const SectionRef, SectionSymbolsTy> &SecSyms : AllSymbols)
array_pod_sort(SecSyms.second.begin(), SecSyms.second.end());
for (const SectionRef &Section : ToolSectionFilter(*Obj)) {
if (!DisassembleAll && (!Section.isText() || Section.isVirtual()))
continue;
uint64_t SectionAddr = Section.getAddress();
uint64_t SectSize = Section.getSize();
if (!SectSize)
continue;
// Get the list of all the symbols in this section.
SectionSymbolsTy &Symbols = AllSymbols[Section];
std::vector<uint64_t> DataMappingSymsAddr;
std::vector<uint64_t> TextMappingSymsAddr;
if (isArmElf(Obj)) {
for (const auto &Symb : Symbols) {
uint64_t Address = std::get<0>(Symb);
StringRef Name = std::get<1>(Symb);
if (Name.startswith("$d"))
DataMappingSymsAddr.push_back(Address - SectionAddr);
if (Name.startswith("$x"))
TextMappingSymsAddr.push_back(Address - SectionAddr);
if (Name.startswith("$a"))
TextMappingSymsAddr.push_back(Address - SectionAddr);
if (Name.startswith("$t"))
TextMappingSymsAddr.push_back(Address - SectionAddr);
}
}
std::sort(DataMappingSymsAddr.begin(), DataMappingSymsAddr.end());
std::sort(TextMappingSymsAddr.begin(), TextMappingSymsAddr.end());
if (Obj->isELF() && Obj->getArch() == Triple::amdgcn) {
// AMDGPU disassembler uses symbolizer for printing labels
std::unique_ptr<MCRelocationInfo> RelInfo(
TheTarget->createMCRelocationInfo(TripleName, Ctx));
if (RelInfo) {
std::unique_ptr<MCSymbolizer> Symbolizer(
TheTarget->createMCSymbolizer(
TripleName, nullptr, nullptr, &Symbols, &Ctx, std::move(RelInfo)));
DisAsm->setSymbolizer(std::move(Symbolizer));
}
}
// Make a list of all the relocations for this section.
std::vector<RelocationRef> Rels;
if (InlineRelocs) {
for (const SectionRef &RelocSec : SectionRelocMap[Section]) {
for (const RelocationRef &Reloc : RelocSec.relocations()) {
Rels.push_back(Reloc);
}
}
}
// Sort relocations by address.
std::sort(Rels.begin(), Rels.end(), RelocAddressLess);
StringRef SegmentName = "";
if (const MachOObjectFile *MachO = dyn_cast<const MachOObjectFile>(Obj)) {
DataRefImpl DR = Section.getRawDataRefImpl();
SegmentName = MachO->getSectionFinalSegmentName(DR);
}
StringRef name;
error(Section.getName(name));
if ((SectionAddr <= StopAddress) &&
(SectionAddr + SectSize) >= StartAddress) {
outs() << "Disassembly of section ";
if (!SegmentName.empty())
outs() << SegmentName << ",";
outs() << name << ':';
}
// If the section has no symbol at the start, just insert a dummy one.
if (Symbols.empty() || std::get<0>(Symbols[0]) != 0) {
Symbols.insert(Symbols.begin(),
std::make_tuple(SectionAddr, name, Section.isText()
? ELF::STT_FUNC
: ELF::STT_OBJECT));
}
SmallString<40> Comments;
raw_svector_ostream CommentStream(Comments);
Add MCSymbolizer for symbolic/annotated disassembly. This is a basic first step towards symbolization of disassembled instructions. This used to be done using externally provided (C API) callbacks. This patch introduces: - the MCSymbolizer class, that mimics the same functions that were used in the X86 and ARM disassemblers to symbolize immediate operands and to annotate loads based off PC (for things like c string literals). - the MCExternalSymbolizer class, which implements the old C API. - the MCRelocationInfo class, which provides a way for targets to translate relocations (either object::RelocationRef, or disassembler C API VariantKinds) to MCExprs. - the MCObjectSymbolizer class, which does symbolization using what it finds in an object::ObjectFile. This makes simple symbolization (with no fancy relocation stuff) work for all object formats! - x86-64 Mach-O and ELF MCRelocationInfos. - A basic ARM Mach-O MCRelocationInfo, that provides just enough to support the C API VariantKinds. Most of what works in otool (the only user of the old symbolization API that I know of) for x86-64 symbolic disassembly (-tvV) works, namely: - symbol references: call _foo; jmp 15 <_foo+50> - relocations: call _foo-_bar; call _foo-4 - __cf?string: leaq 193(%rip), %rax ## literal pool for "hello" Stub support is the main missing part (because libObject doesn't know, among other things, about mach-o indirect symbols). As for the MCSymbolizer API, instead of relying on the disassemblers to call the tryAdding* methods, maybe this could be done automagically using InstrInfo? For instance, even though PC-relative LEAs are used to get the address of string literals in a typical Mach-O file, a MOV would be used in an ELF file. And right now, the explicit symbolization only recognizes PC-relative LEAs. InstrInfo should have already have most of what is needed to know what to symbolize, so this can definitely be improved. I'd also like to remove object::RelocationRef::getValueString (it seems only used by relocation printing in objdump), as simply printing the created MCExpr is definitely enough (and cleaner than string concats). llvm-svn: 182625
2013-05-24 08:39:57 +08:00
StringRef BytesStr;
error(Section.getContents(BytesStr));
ArrayRef<uint8_t> Bytes(reinterpret_cast<const uint8_t *>(BytesStr.data()),
BytesStr.size());
2011-01-20 14:39:06 +08:00
uint64_t Size;
uint64_t Index;
std::vector<RelocationRef>::const_iterator rel_cur = Rels.begin();
std::vector<RelocationRef>::const_iterator rel_end = Rels.end();
// Disassemble symbol by symbol.
for (unsigned si = 0, se = Symbols.size(); si != se; ++si) {
uint64_t Start = std::get<0>(Symbols[si]) - SectionAddr;
// The end is either the section end or the beginning of the next
// symbol.
uint64_t End =
(si == se - 1) ? SectSize : std::get<0>(Symbols[si + 1]) - SectionAddr;
// Don't try to disassemble beyond the end of section contents.
if (End > SectSize)
End = SectSize;
// If this symbol has the same address as the next symbol, then skip it.
if (Start >= End)
continue;
// Check if we need to skip symbol
// Skip if the symbol's data is not between StartAddress and StopAddress
if (End + SectionAddr < StartAddress ||
Start + SectionAddr > StopAddress) {
continue;
}
// Stop disassembly at the stop address specified
if (End + SectionAddr > StopAddress)
End = StopAddress - SectionAddr;
if (Obj->isELF() && Obj->getArch() == Triple::amdgcn) {
// make size 4 bytes folded
End = Start + ((End - Start) & ~0x3ull);
if (std::get<2>(Symbols[si]) == ELF::STT_AMDGPU_HSA_KERNEL) {
// skip amd_kernel_code_t at the begining of kernel symbol (256 bytes)
Start += 256;
}
if (si == se - 1 ||
std::get<2>(Symbols[si + 1]) == ELF::STT_AMDGPU_HSA_KERNEL) {
// cut trailing zeroes at the end of kernel
// cut up to 256 bytes
const uint64_t EndAlign = 256;
const auto Limit = End - (std::min)(EndAlign, End - Start);
while (End > Limit &&
*reinterpret_cast<const support::ulittle32_t*>(&Bytes[End - 4]) == 0)
End -= 4;
}
}
outs() << '\n' << std::get<1>(Symbols[si]) << ":\n";
#ifndef NDEBUG
raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls();
#else
raw_ostream &DebugOut = nulls();
#endif
for (Index = Start; Index < End; Index += Size) {
MCInst Inst;
if (Index + SectionAddr < StartAddress ||
Index + SectionAddr > StopAddress) {
// skip byte by byte till StartAddress is reached
Size = 1;
continue;
}
// AArch64 ELF binaries can interleave data and text in the
// same section. We rely on the markers introduced to
// understand what we need to dump. If the data marker is within a
// function, it is denoted as a word/short etc
if (isArmElf(Obj) && std::get<2>(Symbols[si]) != ELF::STT_OBJECT &&
!DisassembleAll) {
uint64_t Stride = 0;
auto DAI = std::lower_bound(DataMappingSymsAddr.begin(),
DataMappingSymsAddr.end(), Index);
if (DAI != DataMappingSymsAddr.end() && *DAI == Index) {
// Switch to data.
while (Index < End) {
outs() << format("%8" PRIx64 ":", SectionAddr + Index);
outs() << "\t";
if (Index + 4 <= End) {
Stride = 4;
dumpBytes(Bytes.slice(Index, 4), outs());
outs() << "\t.word\t";
uint32_t Data = 0;
if (Obj->isLittleEndian()) {
const auto Word =
reinterpret_cast<const support::ulittle32_t *>(
Bytes.data() + Index);
Data = *Word;
} else {
const auto Word = reinterpret_cast<const support::ubig32_t *>(
Bytes.data() + Index);
Data = *Word;
}
outs() << "0x" << format("%08" PRIx32, Data);
} else if (Index + 2 <= End) {
Stride = 2;
dumpBytes(Bytes.slice(Index, 2), outs());
outs() << "\t\t.short\t";
uint16_t Data = 0;
if (Obj->isLittleEndian()) {
const auto Short =
reinterpret_cast<const support::ulittle16_t *>(
Bytes.data() + Index);
Data = *Short;
} else {
const auto Short =
reinterpret_cast<const support::ubig16_t *>(Bytes.data() +
Index);
Data = *Short;
}
outs() << "0x" << format("%04" PRIx16, Data);
} else {
Stride = 1;
dumpBytes(Bytes.slice(Index, 1), outs());
outs() << "\t\t.byte\t";
outs() << "0x" << format("%02" PRIx8, Bytes.slice(Index, 1)[0]);
}
Index += Stride;
outs() << "\n";
auto TAI = std::lower_bound(TextMappingSymsAddr.begin(),
TextMappingSymsAddr.end(), Index);
if (TAI != TextMappingSymsAddr.end() && *TAI == Index)
break;
}
}
}
// If there is a data symbol inside an ELF text section and we are only
// disassembling text (applicable all architectures),
// we are in a situation where we must print the data and not
// disassemble it.
if (Obj->isELF() && std::get<2>(Symbols[si]) == ELF::STT_OBJECT &&
!DisassembleAll && Section.isText()) {
// print out data up to 8 bytes at a time in hex and ascii
uint8_t AsciiData[9] = {'\0'};
uint8_t Byte;
int NumBytes = 0;
for (Index = Start; Index < End; Index += 1) {
if (((SectionAddr + Index) < StartAddress) ||
((SectionAddr + Index) > StopAddress))
continue;
if (NumBytes == 0) {
outs() << format("%8" PRIx64 ":", SectionAddr + Index);
outs() << "\t";
}
Byte = Bytes.slice(Index)[0];
outs() << format(" %02x", Byte);
AsciiData[NumBytes] = isprint(Byte) ? Byte : '.';
uint8_t IndentOffset = 0;
NumBytes++;
if (Index == End - 1 || NumBytes > 8) {
// Indent the space for less than 8 bytes data.
// 2 spaces for byte and one for space between bytes
IndentOffset = 3 * (8 - NumBytes);
for (int Excess = 8 - NumBytes; Excess < 8; Excess++)
AsciiData[Excess] = '\0';
NumBytes = 8;
}
if (NumBytes == 8) {
AsciiData[8] = '\0';
outs() << std::string(IndentOffset, ' ') << " ";
outs() << reinterpret_cast<char *>(AsciiData);
outs() << '\n';
NumBytes = 0;
}
}
}
if (Index >= End)
break;
// Disassemble a real instruction or a data when disassemble all is
// provided
bool Disassembled = DisAsm->getInstruction(Inst, Size, Bytes.slice(Index),
SectionAddr + Index, DebugOut,
CommentStream);
if (Size == 0)
Size = 1;
PIP.printInst(*IP, Disassembled ? &Inst : nullptr,
Bytes.slice(Index, Size), SectionAddr + Index, outs(), "",
*STI, &SP);
outs() << CommentStream.str();
Comments.clear();
// Try to resolve the target of a call, tail call, etc. to a specific
// symbol.
if (MIA && (MIA->isCall(Inst) || MIA->isUnconditionalBranch(Inst) ||
MIA->isConditionalBranch(Inst))) {
uint64_t Target;
if (MIA->evaluateBranch(Inst, SectionAddr + Index, Size, Target)) {
// In a relocatable object, the target's section must reside in
// the same section as the call instruction or it is accessed
// through a relocation.
//
// In a non-relocatable object, the target may be in any section.
//
// N.B. We don't walk the relocations in the relocatable case yet.
auto *TargetSectionSymbols = &Symbols;
if (!Obj->isRelocatableObject()) {
auto SectionAddress = std::upper_bound(
SectionAddresses.begin(), SectionAddresses.end(), Target,
[](uint64_t LHS,
const std::pair<uint64_t, SectionRef> &RHS) {
return LHS < RHS.first;
});
if (SectionAddress != SectionAddresses.begin()) {
--SectionAddress;
TargetSectionSymbols = &AllSymbols[SectionAddress->second];
} else {
TargetSectionSymbols = nullptr;
}
}
// Find the first symbol in the section whose offset is less than
// or equal to the target.
if (TargetSectionSymbols) {
auto TargetSym = std::upper_bound(
TargetSectionSymbols->begin(), TargetSectionSymbols->end(),
Target, [](uint64_t LHS,
const std::tuple<uint64_t, StringRef, uint8_t> &RHS) {
return LHS < std::get<0>(RHS);
});
if (TargetSym != TargetSectionSymbols->begin()) {
--TargetSym;
uint64_t TargetAddress = std::get<0>(*TargetSym);
StringRef TargetName = std::get<1>(*TargetSym);
outs() << " <" << TargetName;
uint64_t Disp = Target - TargetAddress;
if (Disp)
outs() << "+0x" << utohexstr(Disp);
outs() << '>';
}
}
}
}
outs() << "\n";
// Print relocation for instruction.
while (rel_cur != rel_end) {
bool hidden = getHidden(*rel_cur);
uint64_t addr = rel_cur->getOffset();
SmallString<16> name;
SmallString<32> val;
// If this relocation is hidden, skip it.
if (hidden || ((SectionAddr + addr) < StartAddress)) {
++rel_cur;
continue;
}
// Stop when rel_cur's address is past the current instruction.
if (addr >= Index + Size) break;
rel_cur->getTypeName(name);
error(getRelocationValueString(*rel_cur, val));
outs() << format(Fmt.data(), SectionAddr + addr) << name
<< "\t" << val << "\n";
++rel_cur;
}
}
2011-01-20 14:39:06 +08:00
}
}
}
void llvm::PrintRelocations(const ObjectFile *Obj) {
StringRef Fmt = Obj->getBytesInAddress() > 4 ? "%016" PRIx64 :
"%08" PRIx64;
// Regular objdump doesn't print relocations in non-relocatable object
// files.
if (!Obj->isRelocatableObject())
return;
for (const SectionRef &Section : ToolSectionFilter(*Obj)) {
if (Section.relocation_begin() == Section.relocation_end())
continue;
StringRef secname;
error(Section.getName(secname));
outs() << "RELOCATION RECORDS FOR [" << secname << "]:\n";
for (const RelocationRef &Reloc : Section.relocations()) {
bool hidden = getHidden(Reloc);
uint64_t address = Reloc.getOffset();
SmallString<32> relocname;
SmallString<32> valuestr;
if (address < StartAddress || address > StopAddress || hidden)
continue;
Reloc.getTypeName(relocname);
error(getRelocationValueString(Reloc, valuestr));
outs() << format(Fmt.data(), address) << " " << relocname << " "
<< valuestr << "\n";
}
outs() << "\n";
}
}
void llvm::PrintSectionHeaders(const ObjectFile *Obj) {
outs() << "Sections:\n"
"Idx Name Size Address Type\n";
unsigned i = 0;
for (const SectionRef &Section : ToolSectionFilter(*Obj)) {
StringRef Name;
error(Section.getName(Name));
uint64_t Address = Section.getAddress();
uint64_t Size = Section.getSize();
bool Text = Section.isText();
bool Data = Section.isData();
bool BSS = Section.isBSS();
std::string Type = (std::string(Text ? "TEXT " : "") +
(Data ? "DATA " : "") + (BSS ? "BSS" : ""));
outs() << format("%3d %-13s %08" PRIx64 " %016" PRIx64 " %s\n", i,
Name.str().c_str(), Size, Address, Type.c_str());
++i;
}
}
void llvm::PrintSectionContents(const ObjectFile *Obj) {
std::error_code EC;
for (const SectionRef &Section : ToolSectionFilter(*Obj)) {
StringRef Name;
StringRef Contents;
error(Section.getName(Name));
uint64_t BaseAddr = Section.getAddress();
uint64_t Size = Section.getSize();
if (!Size)
continue;
outs() << "Contents of section " << Name << ":\n";
if (Section.isBSS()) {
outs() << format("<skipping contents of bss section at [%04" PRIx64
", %04" PRIx64 ")>\n",
BaseAddr, BaseAddr + Size);
continue;
}
error(Section.getContents(Contents));
// Dump out the content as hex and printable ascii characters.
for (std::size_t addr = 0, end = Contents.size(); addr < end; addr += 16) {
outs() << format(" %04" PRIx64 " ", BaseAddr + addr);
// Dump line of hex.
for (std::size_t i = 0; i < 16; ++i) {
if (i != 0 && i % 4 == 0)
outs() << ' ';
if (addr + i < end)
outs() << hexdigit((Contents[addr + i] >> 4) & 0xF, true)
<< hexdigit(Contents[addr + i] & 0xF, true);
else
outs() << " ";
}
// Print ascii.
outs() << " ";
for (std::size_t i = 0; i < 16 && addr + i < end; ++i) {
if (std::isprint(static_cast<unsigned char>(Contents[addr + i]) & 0xFF))
outs() << Contents[addr + i];
else
outs() << ".";
}
outs() << "\n";
}
}
}
void llvm::PrintSymbolTable(const ObjectFile *o, StringRef ArchiveName,
StringRef ArchitectureName) {
outs() << "SYMBOL TABLE:\n";
if (const COFFObjectFile *coff = dyn_cast<const COFFObjectFile>(o)) {
printCOFFSymbolTable(coff);
return;
}
for (const SymbolRef &Symbol : o->symbols()) {
Expected<uint64_t> AddressOrError = Symbol.getAddress();
if (!AddressOrError)
report_error(ArchiveName, o->getFileName(), AddressOrError.takeError(),
ArchitectureName);
uint64_t Address = *AddressOrError;
if ((Address < StartAddress) || (Address > StopAddress))
continue;
Expected<SymbolRef::Type> TypeOrError = Symbol.getType();
if (!TypeOrError)
report_error(ArchiveName, o->getFileName(), TypeOrError.takeError(),
ArchitectureName);
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
2016-03-24 04:27:00 +08:00
SymbolRef::Type Type = *TypeOrError;
uint32_t Flags = Symbol.getFlags();
Expected<section_iterator> SectionOrErr = Symbol.getSection();
if (!SectionOrErr)
report_error(ArchiveName, o->getFileName(), SectionOrErr.takeError(),
ArchitectureName);
section_iterator Section = *SectionOrErr;
StringRef Name;
if (Type == SymbolRef::ST_Debug && Section != o->section_end()) {
Section->getName(Name);
} else {
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
2016-04-21 05:24:34 +08:00
Expected<StringRef> NameOrErr = Symbol.getName();
if (!NameOrErr)
report_error(ArchiveName, o->getFileName(), NameOrErr.takeError(),
ArchitectureName);
Name = *NameOrErr;
}
bool Global = Flags & SymbolRef::SF_Global;
bool Weak = Flags & SymbolRef::SF_Weak;
bool Absolute = Flags & SymbolRef::SF_Absolute;
bool Common = Flags & SymbolRef::SF_Common;
bool Hidden = Flags & SymbolRef::SF_Hidden;
char GlobLoc = ' ';
if (Type != SymbolRef::ST_Unknown)
GlobLoc = Global ? 'g' : 'l';
char Debug = (Type == SymbolRef::ST_Debug || Type == SymbolRef::ST_File)
? 'd' : ' ';
char FileFunc = ' ';
if (Type == SymbolRef::ST_File)
FileFunc = 'f';
else if (Type == SymbolRef::ST_Function)
FileFunc = 'F';
const char *Fmt = o->getBytesInAddress() > 4 ? "%016" PRIx64 :
"%08" PRIx64;
outs() << format(Fmt, Address) << " "
<< GlobLoc // Local -> 'l', Global -> 'g', Neither -> ' '
<< (Weak ? 'w' : ' ') // Weak?
<< ' ' // Constructor. Not supported yet.
<< ' ' // Warning. Not supported yet.
<< ' ' // Indirect reference to another symbol.
<< Debug // Debugging (d) or dynamic (D) symbol.
<< FileFunc // Name of function (F), file (f) or object (O).
<< ' ';
if (Absolute) {
outs() << "*ABS*";
} else if (Common) {
outs() << "*COM*";
} else if (Section == o->section_end()) {
outs() << "*UND*";
} else {
if (const MachOObjectFile *MachO =
dyn_cast<const MachOObjectFile>(o)) {
DataRefImpl DR = Section->getRawDataRefImpl();
StringRef SegmentName = MachO->getSectionFinalSegmentName(DR);
outs() << SegmentName << ",";
}
StringRef SectionName;
error(Section->getName(SectionName));
outs() << SectionName;
}
outs() << '\t';
if (Common || isa<ELFObjectFileBase>(o)) {
uint64_t Val =
Common ? Symbol.getAlignment() : ELFSymbolRef(Symbol).getSize();
outs() << format("\t %08" PRIx64 " ", Val);
}
if (Hidden) {
outs() << ".hidden ";
}
outs() << Name
<< '\n';
}
}
static void PrintUnwindInfo(const ObjectFile *o) {
outs() << "Unwind info:\n\n";
if (const COFFObjectFile *coff = dyn_cast<COFFObjectFile>(o)) {
printCOFFUnwindInfo(coff);
} else if (const MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o))
printMachOUnwindInfo(MachO);
else {
// TODO: Extract DWARF dump tool to objdump.
errs() << "This operation is only currently supported "
"for COFF and MachO object files.\n";
return;
}
}
void llvm::printExportsTrie(const ObjectFile *o) {
outs() << "Exports trie:\n";
if (const MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o))
printMachOExportsTrie(MachO);
else {
errs() << "This operation is only currently supported "
"for Mach-O executable files.\n";
return;
}
}
void llvm::printRebaseTable(const ObjectFile *o) {
outs() << "Rebase table:\n";
if (const MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o))
printMachORebaseTable(MachO);
else {
errs() << "This operation is only currently supported "
"for Mach-O executable files.\n";
return;
}
}
void llvm::printBindTable(const ObjectFile *o) {
outs() << "Bind table:\n";
if (const MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o))
printMachOBindTable(MachO);
else {
errs() << "This operation is only currently supported "
"for Mach-O executable files.\n";
return;
}
}
void llvm::printLazyBindTable(const ObjectFile *o) {
outs() << "Lazy bind table:\n";
if (const MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o))
printMachOLazyBindTable(MachO);
else {
errs() << "This operation is only currently supported "
"for Mach-O executable files.\n";
return;
}
}
void llvm::printWeakBindTable(const ObjectFile *o) {
outs() << "Weak bind table:\n";
if (const MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o))
printMachOWeakBindTable(MachO);
else {
errs() << "This operation is only currently supported "
"for Mach-O executable files.\n";
return;
}
}
/// Dump the raw contents of the __clangast section so the output can be piped
/// into llvm-bcanalyzer.
void llvm::printRawClangAST(const ObjectFile *Obj) {
if (outs().is_displayed()) {
errs() << "The -raw-clang-ast option will dump the raw binary contents of "
"the clang ast section.\n"
"Please redirect the output to a file or another program such as "
"llvm-bcanalyzer.\n";
return;
}
StringRef ClangASTSectionName("__clangast");
if (isa<COFFObjectFile>(Obj)) {
ClangASTSectionName = "clangast";
}
Optional<object::SectionRef> ClangASTSection;
for (auto Sec : ToolSectionFilter(*Obj)) {
StringRef Name;
Sec.getName(Name);
if (Name == ClangASTSectionName) {
ClangASTSection = Sec;
break;
}
}
if (!ClangASTSection)
return;
StringRef ClangASTContents;
error(ClangASTSection.getValue().getContents(ClangASTContents));
outs().write(ClangASTContents.data(), ClangASTContents.size());
}
static void printFaultMaps(const ObjectFile *Obj) {
const char *FaultMapSectionName = nullptr;
if (isa<ELFObjectFileBase>(Obj)) {
FaultMapSectionName = ".llvm_faultmaps";
} else if (isa<MachOObjectFile>(Obj)) {
FaultMapSectionName = "__llvm_faultmaps";
} else {
errs() << "This operation is only currently supported "
"for ELF and Mach-O executable files.\n";
return;
}
Optional<object::SectionRef> FaultMapSection;
for (auto Sec : ToolSectionFilter(*Obj)) {
StringRef Name;
Sec.getName(Name);
if (Name == FaultMapSectionName) {
FaultMapSection = Sec;
break;
}
}
outs() << "FaultMap table:\n";
if (!FaultMapSection.hasValue()) {
outs() << "<not found>\n";
return;
}
StringRef FaultMapContents;
error(FaultMapSection.getValue().getContents(FaultMapContents));
FaultMapParser FMP(FaultMapContents.bytes_begin(),
FaultMapContents.bytes_end());
outs() << FMP;
}
static void printPrivateFileHeaders(const ObjectFile *o, bool onlyFirst) {
if (o->isELF())
return printELFFileHeader(o);
if (o->isCOFF())
return printCOFFFileHeader(o);
if (o->isWasm())
return printWasmFileHeader(o);
if (o->isMachO()) {
printMachOFileHeader(o);
if (!onlyFirst)
printMachOLoadCommands(o);
return;
}
report_error(o->getFileName(), "Invalid/Unsupported object file format");
}
static void DumpObject(const ObjectFile *o, const Archive *a = nullptr) {
StringRef ArchiveName = a != nullptr ? a->getFileName() : "";
// Avoid other output when using a raw option.
if (!RawClangAST) {
outs() << '\n';
if (a)
outs() << a->getFileName() << "(" << o->getFileName() << ")";
else
outs() << o->getFileName();
outs() << ":\tfile format " << o->getFileFormatName() << "\n\n";
}
if (Disassemble)
DisassembleObject(o, Relocations);
if (Relocations && !Disassemble)
PrintRelocations(o);
if (SectionHeaders)
PrintSectionHeaders(o);
if (SectionContents)
PrintSectionContents(o);
if (SymbolTable)
PrintSymbolTable(o, ArchiveName);
if (UnwindInfo)
PrintUnwindInfo(o);
if (PrivateHeaders || FirstPrivateHeader)
printPrivateFileHeaders(o, FirstPrivateHeader);
if (ExportsTrie)
printExportsTrie(o);
if (Rebase)
printRebaseTable(o);
if (Bind)
printBindTable(o);
if (LazyBind)
printLazyBindTable(o);
if (WeakBind)
printWeakBindTable(o);
if (RawClangAST)
printRawClangAST(o);
if (PrintFaultMaps)
printFaultMaps(o);
if (DwarfDumpType != DIDT_Null) {
std::unique_ptr<DIContext> DICtx(new DWARFContextInMemory(*o));
// Dump the complete DWARF structure.
DICtx->dump(outs(), DwarfDumpType, true /* DumpEH */);
}
}
static void DumpObject(const COFFImportFile *I, const Archive *A) {
StringRef ArchiveName = A ? A->getFileName() : "";
// Avoid other output when using a raw option.
if (!RawClangAST)
outs() << '\n'
<< ArchiveName << "(" << I->getFileName() << ")"
<< ":\tfile format COFF-import-file"
<< "\n\n";
if (SymbolTable)
printCOFFSymbolTable(I);
}
/// @brief Dump each object file in \a a;
static void DumpArchive(const Archive *a) {
Error Err = Error::success();
for (auto &C : a->children(Err)) {
Expected<std::unique_ptr<Binary>> ChildOrErr = C.getAsBinary();
if (!ChildOrErr) {
if (auto E = isNotObjectErrorInvalidFileType(ChildOrErr.takeError()))
report_error(a->getFileName(), C, std::move(E));
continue;
}
if (ObjectFile *o = dyn_cast<ObjectFile>(&*ChildOrErr.get()))
DumpObject(o, a);
else if (COFFImportFile *I = dyn_cast<COFFImportFile>(&*ChildOrErr.get()))
DumpObject(I, a);
else
report_error(a->getFileName(), object_error::invalid_file_type);
}
if (Err)
report_error(a->getFileName(), std::move(Err));
}
/// @brief Open file and figure out how to dump it.
static void DumpInput(StringRef file) {
// If we are using the Mach-O specific object file parser, then let it parse
// the file and process the command line options. So the -arch flags can
// be used to select specific slices, etc.
if (MachOOpt) {
ParseInputMachO(file);
return;
}
// Attempt to open the binary.
Thread Expected<...> up from createMachOObjectFile() to allow llvm-objdump to produce a real error message Produce the first specific error message for a malformed Mach-O file describing the problem instead of the generic message for object_error::parse_failed of "Invalid data was encountered while parsing the file”.  Many more good error messages will follow after this first one. This is built on Lang Hames’ great work of adding the ’Error' class for structured error handling and threading Error through MachOObjectFile construction. And making createMachOObjectFile return Expected<...> . So to to get the error to the llvm-obdump tool, I changed the stack of these methods to also return Expected<...> : object::ObjectFile::createObjectFile() object::SymbolicFile::createSymbolicFile() object::createBinary() Then finally in ParseInputMachO() in MachODump.cpp the error can be reported and the specific error message can be printed in llvm-objdump and can be seen in the existing test case for the existing malformed binary but with the updated error message. Converting these interfaces to Expected<> from ErrorOr<> does involve touching a number of places. To contain the changes for now use of errorToErrorCode() and errorOrToExpected() are used where the callers are yet to be converted. 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(ObjOrErr.takeError()) so the buggy code will not crash since needed to deal with the Error. Note there is one fix also needed to lld/COFF/InputFiles.cpp 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: 265606
2016-04-07 06:14:09 +08:00
Expected<OwningBinary<Binary>> BinaryOrErr = createBinary(file);
if (!BinaryOrErr)
report_error(file, BinaryOrErr.takeError());
Binary &Binary = *BinaryOrErr.get().getBinary();
if (Archive *a = dyn_cast<Archive>(&Binary))
DumpArchive(a);
else if (ObjectFile *o = dyn_cast<ObjectFile>(&Binary))
DumpObject(o);
2012-08-08 01:53:14 +08:00
else
report_error(file, object_error::invalid_file_type);
}
2011-01-20 14:39:06 +08:00
int main(int argc, char **argv) {
// Print a stack trace if we signal out.
sys::PrintStackTraceOnErrorSignal(argv[0]);
2011-01-20 14:39:06 +08:00
PrettyStackTraceProgram X(argc, argv);
llvm_shutdown_obj Y; // Call llvm_shutdown() on exit.
// Initialize targets and assembly printers/parsers.
llvm::InitializeAllTargetInfos();
llvm::InitializeAllTargetMCs();
2011-01-20 14:39:06 +08:00
llvm::InitializeAllDisassemblers();
// Register the target printer for --version.
cl::AddExtraVersionPrinter(TargetRegistry::printRegisteredTargetsForVersion);
2011-01-20 14:39:06 +08:00
cl::ParseCommandLineOptions(argc, argv, "llvm object file dumper\n");
TripleName = Triple::normalize(TripleName);
ToolName = argv[0];
// Defaults to a.out if no filenames specified.
if (InputFilenames.size() == 0)
InputFilenames.push_back("a.out");
if (DisassembleAll || PrintSource || PrintLines)
Disassemble = true;
if (!Disassemble
&& !Relocations
&& !SectionHeaders
&& !SectionContents
&& !SymbolTable
&& !UnwindInfo
&& !PrivateHeaders
&& !FirstPrivateHeader
&& !ExportsTrie
&& !Rebase
&& !Bind
&& !LazyBind
&& !WeakBind
&& !RawClangAST
&& !(UniversalHeaders && MachOOpt)
&& !(ArchiveHeaders && MachOOpt)
&& !(IndirectSymbols && MachOOpt)
&& !(DataInCode && MachOOpt)
&& !(LinkOptHints && MachOOpt)
&& !(InfoPlist && MachOOpt)
&& !(DylibsUsed && MachOOpt)
&& !(DylibId && MachOOpt)
&& !(ObjcMetaData && MachOOpt)
&& !(FilterSections.size() != 0 && MachOOpt)
&& !PrintFaultMaps
&& DwarfDumpType == DIDT_Null) {
2011-01-20 14:39:06 +08:00
cl::PrintHelpMessage();
return 2;
}
std::for_each(InputFilenames.begin(), InputFilenames.end(),
DumpInput);
2011-01-20 14:39:06 +08:00
return EXIT_SUCCESS;
2011-01-20 14:39:06 +08:00
}