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.
|
|
|
|
//
|
2013-02-06 04:27:22 +08:00
|
|
|
// The flags and output of this program should be near identical to those of
|
|
|
|
// binutils objdump.
|
|
|
|
//
|
2011-01-20 14:39:06 +08:00
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
2011-09-20 01:56:04 +08:00
|
|
|
#include "llvm-objdump.h"
|
2015-06-23 02:03:02 +08:00
|
|
|
#include "llvm/ADT/Optional.h"
|
2012-12-04 18:44:52 +08:00
|
|
|
#include "llvm/ADT/STLExtras.h"
|
2011-10-18 01:13:22 +08:00
|
|
|
#include "llvm/ADT/StringExtras.h"
|
2011-01-20 14:39:06 +08:00
|
|
|
#include "llvm/ADT/Triple.h"
|
2015-06-24 04:09:03 +08:00
|
|
|
#include "llvm/CodeGen/FaultMaps.h"
|
2016-01-26 23:09:42 +08:00
|
|
|
#include "llvm/DebugInfo/DWARF/DWARFContext.h"
|
2016-08-16 03:49:24 +08:00
|
|
|
#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"
|
2016-01-27 00:44:37 +08:00
|
|
|
#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"
|
2012-04-02 14:09:36 +08:00
|
|
|
#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"
|
2012-03-06 03:33:20 +08:00
|
|
|
#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"
|
2012-12-04 18:44:52 +08:00
|
|
|
#include "llvm/Object/Archive.h"
|
|
|
|
#include "llvm/Object/COFF.h"
|
2016-08-19 00:39:19 +08:00
|
|
|
#include "llvm/Object/COFFImportFile.h"
|
2016-01-27 00:44:37 +08:00
|
|
|
#include "llvm/Object/ELFObjectFile.h"
|
Add a function to get the segment name of a section.
On MachO, sections also have segment names. When a tool looking at a .o file
prints a segment name, this is what they mean. In reality, a .o has only one
anonymous, segment.
This patch adds a MachO only function to fetch that segment name. I named it
getSectionFinalSegmentName since the main use for the name seems to be inform
the linker with segment this section should go to.
The patch also changes MachOObjectFile::getSectionName to return just the
section name instead of computing SegmentName,SectionName.
The main difference from the previous patch is that it doesn't use
InMemoryStruct. It is extremely dangerous: if the endians match it returns
a pointer to the file buffer, if not, it returns a pointer to an internal buffer
that is overwritten in the next API call.
We should change all of this code to use
support::detail::packed_endian_specific_integral like ELF, but since these
functions only handle strings, they work with big and little endian machines
as is.
I have tested this by installing ubuntu 12.10 ppc on qemu, that is why it took
so long :-)
llvm-svn: 170838
2012-12-21 11:47:03 +08:00
|
|
|
#include "llvm/Object/MachO.h"
|
2012-12-04 18:44:52 +08:00
|
|
|
#include "llvm/Object/ObjectFile.h"
|
2011-10-08 08:18:30 +08:00
|
|
|
#include "llvm/Support/Casting.h"
|
2011-01-20 14:39:06 +08:00
|
|
|
#include "llvm/Support/CommandLine.h"
|
|
|
|
#include "llvm/Support/Debug.h"
|
2015-06-05 02:34:11 +08:00
|
|
|
#include "llvm/Support/Errc.h"
|
2011-10-08 08:18:30 +08:00
|
|
|
#include "llvm/Support/FileSystem.h"
|
2011-01-20 14:39:06 +08:00
|
|
|
#include "llvm/Support/Format.h"
|
2011-07-26 07:04:36 +08:00
|
|
|
#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"
|
2011-08-25 02:08:43 +08:00
|
|
|
#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>
|
2012-03-23 19:49:32 +08:00
|
|
|
#include <cctype>
|
2011-01-20 14:39:06 +08:00
|
|
|
#include <cstring>
|
2014-06-13 01:38:55 +08:00
|
|
|
#include <system_error>
|
2016-05-27 22:27:24 +08:00
|
|
|
#include <utility>
|
2016-08-16 03:49:24 +08:00
|
|
|
#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;
|
|
|
|
|
2011-09-20 01:56:04 +08:00
|
|
|
static cl::list<std::string>
|
|
|
|
InputFilenames(cl::Positional, cl::desc("<input object files>"),cl::ZeroOrMore);
|
2011-01-20 14:39:06 +08:00
|
|
|
|
2015-01-08 05:02:18 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::Disassemble("disassemble",
|
2011-09-20 01:56:04 +08:00
|
|
|
cl::desc("Display assembler mnemonics for the machine instructions"));
|
|
|
|
static cl::alias
|
|
|
|
Disassembled("d", cl::desc("Alias for --disassemble"),
|
2015-07-29 23:45:39 +08:00
|
|
|
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"),
|
2015-07-24 04:58:49 +08:00
|
|
|
cl::aliasopt(DisassembleAll));
|
2011-01-20 14:39:06 +08:00
|
|
|
|
2015-01-21 05:47:46 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::Relocations("r", cl::desc("Display the relocation entries in the file"));
|
2011-10-08 08:18:30 +08:00
|
|
|
|
2015-01-21 05:47:46 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::SectionContents("s", cl::desc("Display the content of each section"));
|
2011-10-18 01:13:22 +08:00
|
|
|
|
2015-01-21 05:47:46 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::SymbolTable("t", cl::desc("Display the symbol table"));
|
2011-10-19 03:32:17 +08:00
|
|
|
|
2015-01-08 05:02:18 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::ExportsTrie("exports-trie", cl::desc("Display mach-o exported symbols"));
|
2014-08-30 08:20:14 +08:00
|
|
|
|
2015-01-08 05:02:18 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::Rebase("rebase", cl::desc("Display mach-o rebasing info"));
|
2014-09-13 05:34:15 +08:00
|
|
|
|
2015-01-08 05:02:18 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::Bind("bind", cl::desc("Display mach-o binding info"));
|
2014-09-16 09:41:51 +08:00
|
|
|
|
2015-01-08 05:02:18 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::LazyBind("lazy-bind", cl::desc("Display mach-o lazy binding info"));
|
2014-09-16 09:41:51 +08:00
|
|
|
|
2015-01-08 05:02:18 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::WeakBind("weak-bind", cl::desc("Display mach-o weak binding info"));
|
2014-09-16 09:41:51 +08:00
|
|
|
|
2015-07-08 10:04:15 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::RawClangAST("raw-clang-ast",
|
|
|
|
cl::desc("Dump the raw binary contents of the clang AST section"));
|
|
|
|
|
2011-09-20 01:56:04 +08:00
|
|
|
static cl::opt<bool>
|
Add a function to get the segment name of a section.
On MachO, sections also have segment names. When a tool looking at a .o file
prints a segment name, this is what they mean. In reality, a .o has only one
anonymous, segment.
This patch adds a MachO only function to fetch that segment name. I named it
getSectionFinalSegmentName since the main use for the name seems to be inform
the linker with segment this section should go to.
The patch also changes MachOObjectFile::getSectionName to return just the
section name instead of computing SegmentName,SectionName.
The main difference from the previous patch is that it doesn't use
InMemoryStruct. It is extremely dangerous: if the endians match it returns
a pointer to the file buffer, if not, it returns a pointer to an internal buffer
that is overwritten in the next API call.
We should change all of this code to use
support::detail::packed_endian_specific_integral like ELF, but since these
functions only handle strings, they work with big and little endian machines
as is.
I have tested this by installing ubuntu 12.10 ppc on qemu, that is why it took
so long :-)
llvm-svn: 170838
2012-12-21 11:47:03 +08:00
|
|
|
MachOOpt("macho", cl::desc("Use MachO specific object file parser"));
|
2011-09-20 01:56:04 +08:00
|
|
|
static cl::alias
|
Add a function to get the segment name of a section.
On MachO, sections also have segment names. When a tool looking at a .o file
prints a segment name, this is what they mean. In reality, a .o has only one
anonymous, segment.
This patch adds a MachO only function to fetch that segment name. I named it
getSectionFinalSegmentName since the main use for the name seems to be inform
the linker with segment this section should go to.
The patch also changes MachOObjectFile::getSectionName to return just the
section name instead of computing SegmentName,SectionName.
The main difference from the previous patch is that it doesn't use
InMemoryStruct. It is extremely dangerous: if the endians match it returns
a pointer to the file buffer, if not, it returns a pointer to an internal buffer
that is overwritten in the next API call.
We should change all of this code to use
support::detail::packed_endian_specific_integral like ELF, but since these
functions only handle strings, they work with big and little endian machines
as is.
I have tested this by installing ubuntu 12.10 ppc on qemu, that is why it took
so long :-)
llvm-svn: 170838
2012-12-21 11:47:03 +08:00
|
|
|
MachOm("m", cl::desc("Alias for --macho"), cl::aliasopt(MachOOpt));
|
2011-07-21 03:37:35 +08:00
|
|
|
|
2011-09-20 01:56:04 +08:00
|
|
|
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
|
|
|
|
2014-08-07 07:24:41 +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(""));
|
|
|
|
|
2011-09-20 01:56:04 +08:00
|
|
|
cl::opt<std::string>
|
2014-12-05 07:56:27 +08:00
|
|
|
llvm::ArchName("arch-name", cl::desc("Target arch to disassemble for, "
|
2011-09-20 01:56:04 +08:00
|
|
|
"see -version for available targets"));
|
2011-01-20 14:39:06 +08:00
|
|
|
|
2015-01-21 05:47:46 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::SectionHeaders("section-headers", cl::desc("Display summaries of the "
|
|
|
|
"headers for each section."));
|
2011-10-11 05:21:34 +08:00
|
|
|
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));
|
2015-07-30 03:08:10 +08:00
|
|
|
|
2015-07-29 23:45:39 +08:00
|
|
|
cl::list<std::string>
|
2015-07-30 03:08:10 +08:00
|
|
|
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));
|
2011-10-11 05:21:34 +08:00
|
|
|
|
2014-08-07 07:24:41 +08:00
|
|
|
cl::list<std::string>
|
|
|
|
llvm::MAttrs("mattr",
|
2012-08-29 03:24:49 +08:00
|
|
|
cl::CommaSeparated,
|
|
|
|
cl::desc("Target specific attributes"),
|
|
|
|
cl::value_desc("a1,+a2,-a3,..."));
|
|
|
|
|
2014-09-25 07:08:22 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::NoShowRawInsn("no-show-raw-insn", cl::desc("When disassembling "
|
|
|
|
"instructions, do not print "
|
|
|
|
"the instruction bytes."));
|
2012-11-21 06:57:02 +08:00
|
|
|
|
2015-01-21 05:47:46 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::UnwindInfo("unwind-info", cl::desc("Display unwind information"));
|
2012-12-06 04:12:35 +08:00
|
|
|
|
|
|
|
static cl::alias
|
|
|
|
UnwindInfoShort("u", cl::desc("Alias for --unwind-info"),
|
|
|
|
cl::aliasopt(UnwindInfo));
|
|
|
|
|
2015-01-08 05:02:18 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::PrivateHeaders("private-headers",
|
|
|
|
cl::desc("Display format specific file headers"));
|
2013-01-06 11:56:49 +08:00
|
|
|
|
2016-01-13 08:25:36 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::FirstPrivateHeader("private-header",
|
|
|
|
cl::desc("Display only the first format specific file "
|
|
|
|
"header"));
|
|
|
|
|
2013-01-06 11:56:49 +08:00
|
|
|
static cl::alias
|
|
|
|
PrivateHeadersShort("p", cl::desc("Alias for --private-headers"),
|
|
|
|
cl::aliasopt(PrivateHeaders));
|
|
|
|
|
2015-06-08 05:07:17 +08:00
|
|
|
cl::opt<bool>
|
|
|
|
llvm::PrintImmHex("print-imm-hex",
|
2016-04-09 02:15:37 +08:00
|
|
|
cl::desc("Use hex format for immediate values"));
|
2015-06-08 05:07:17 +08:00
|
|
|
|
2015-06-23 02:03:02 +08:00
|
|
|
cl::opt<bool> PrintFaultMaps("fault-map-section",
|
|
|
|
cl::desc("Display contents of faultmap section"));
|
|
|
|
|
2016-01-26 23:09:42 +08:00
|
|
|
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"),
|
|
|
|
clEnumValEnd));
|
|
|
|
|
2016-08-16 03:49:24 +08:00
|
|
|
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));
|
2016-09-13 01:08:22 +08:00
|
|
|
|
|
|
|
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));
|
2011-09-20 01:56:04 +08:00
|
|
|
static StringRef ToolName;
|
2011-06-26 01:55:23 +08:00
|
|
|
|
2015-07-29 23:45:39 +08:00
|
|
|
namespace {
|
2015-07-30 03:08:10 +08:00
|
|
|
typedef std::function<bool(llvm::object::SectionRef const &)> FilterPredicate;
|
2015-07-29 23:45:39 +08:00
|
|
|
|
|
|
|
class SectionFilterIterator {
|
|
|
|
public:
|
|
|
|
SectionFilterIterator(FilterPredicate P,
|
|
|
|
llvm::object::section_iterator const &I,
|
|
|
|
llvm::object::section_iterator const &E)
|
2016-05-27 22:27:24 +08:00
|
|
|
: Predicate(std::move(P)), Iterator(I), End(E) {
|
2015-07-29 23:45:39 +08:00
|
|
|
ScanPredicate();
|
|
|
|
}
|
2015-09-24 22:52:52 +08:00
|
|
|
const llvm::object::SectionRef &operator*() const { return *Iterator; }
|
2015-07-29 23:45:39 +08:00
|
|
|
SectionFilterIterator &operator++() {
|
|
|
|
++Iterator;
|
|
|
|
ScanPredicate();
|
|
|
|
return *this;
|
|
|
|
}
|
|
|
|
bool operator!=(SectionFilterIterator const &Other) const {
|
|
|
|
return Iterator != Other.Iterator;
|
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
void ScanPredicate() {
|
2015-07-30 03:21:13 +08:00
|
|
|
while (Iterator != End && !Predicate(*Iterator)) {
|
2015-07-29 23:45:39 +08:00
|
|
|
++Iterator;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
FilterPredicate Predicate;
|
|
|
|
llvm::object::section_iterator Iterator;
|
|
|
|
llvm::object::section_iterator End;
|
|
|
|
};
|
|
|
|
|
|
|
|
class SectionFilter {
|
|
|
|
public:
|
|
|
|
SectionFilter(FilterPredicate P, llvm::object::ObjectFile const &O)
|
2016-05-27 22:27:24 +08:00
|
|
|
: Predicate(std::move(P)), Object(O) {}
|
2015-07-29 23:45:39 +08:00
|
|
|
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) {
|
2016-08-12 11:55:06 +08:00
|
|
|
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);
|
2015-07-29 23:45:39 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-08-05 15:18:31 +08:00
|
|
|
void llvm::error(std::error_code EC) {
|
2014-01-25 08:32:01 +08:00
|
|
|
if (!EC)
|
2015-08-05 15:18:31 +08:00
|
|
|
return;
|
2011-06-26 01:55:23 +08:00
|
|
|
|
2015-12-26 02:16:45 +08:00
|
|
|
errs() << ToolName << ": error reading file: " << EC.message() << ".\n";
|
|
|
|
errs().flush();
|
2015-08-06 08:18:52 +08:00
|
|
|
exit(1);
|
2011-01-20 14:39:06 +08:00
|
|
|
}
|
|
|
|
|
2016-06-29 07:16:13 +08:00
|
|
|
LLVM_ATTRIBUTE_NORETURN void llvm::error(Twine Message) {
|
|
|
|
errs() << ToolName << ": " << Message << ".\n";
|
|
|
|
errs().flush();
|
|
|
|
exit(1);
|
|
|
|
}
|
|
|
|
|
2015-12-29 21:41:02 +08:00
|
|
|
LLVM_ATTRIBUTE_NORETURN void llvm::report_error(StringRef File,
|
|
|
|
std::error_code EC) {
|
2015-06-05 02:34:11 +08:00
|
|
|
assert(EC);
|
|
|
|
errs() << ToolName << ": '" << File << "': " << EC.message() << ".\n";
|
2015-08-05 15:18:31 +08:00
|
|
|
exit(1);
|
2015-06-05 02:34:11 +08:00
|
|
|
}
|
|
|
|
|
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();
|
2016-05-06 01:43:35 +08:00
|
|
|
errs() << ToolName << ": '" << File << "': " << Buf;
|
2016-04-07 06:14:09 +08:00
|
|
|
exit(1);
|
|
|
|
}
|
|
|
|
|
2016-05-18 01:10:12 +08:00
|
|
|
LLVM_ATTRIBUTE_NORETURN void llvm::report_error(StringRef ArchiveName,
|
|
|
|
StringRef FileName,
|
2016-06-01 04:35:34 +08:00
|
|
|
llvm::Error E,
|
|
|
|
StringRef ArchitectureName) {
|
2016-05-18 01:10:12 +08:00
|
|
|
assert(E);
|
|
|
|
errs() << ToolName << ": ";
|
|
|
|
if (ArchiveName != "")
|
|
|
|
errs() << ArchiveName << "(" << FileName << ")";
|
|
|
|
else
|
|
|
|
errs() << FileName;
|
2016-06-01 04:35:34 +08:00
|
|
|
if (!ArchitectureName.empty())
|
|
|
|
errs() << " (for architecture " << ArchitectureName << ")";
|
2016-05-18 01:10:12 +08:00
|
|
|
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,
|
2016-06-01 04:35:34 +08:00
|
|
|
llvm::Error E,
|
|
|
|
StringRef ArchitectureName) {
|
2016-07-30 01:44:13 +08:00
|
|
|
Expected<StringRef> NameOrErr = C.getName();
|
2016-05-18 01:10:12 +08:00
|
|
|
// 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.
|
2016-07-30 01:44:13 +08:00
|
|
|
if (!NameOrErr) {
|
|
|
|
consumeError(NameOrErr.takeError());
|
2016-06-01 04:35:34 +08:00
|
|
|
llvm::report_error(ArchiveName, "???", std::move(E), ArchitectureName);
|
2016-07-30 01:44:13 +08:00
|
|
|
} else
|
2016-06-01 04:35:34 +08:00
|
|
|
llvm::report_error(ArchiveName, NameOrErr.get(), std::move(E),
|
|
|
|
ArchitectureName);
|
2016-05-18 01:10:12 +08:00
|
|
|
}
|
|
|
|
|
2014-04-25 12:24:47 +08:00
|
|
|
static const Target *getTarget(const ObjectFile *Obj = nullptr) {
|
2011-01-20 14:39:06 +08:00
|
|
|
// Figure out the target triple.
|
2012-05-09 07:38:45 +08:00
|
|
|
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) {
|
2012-05-09 07:38:45 +08:00
|
|
|
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())
|
2014-03-07 04:47:11 +08:00
|
|
|
TheTriple.setObjectFormat(Triple::MachO);
|
2014-04-17 14:17:23 +08:00
|
|
|
|
|
|
|
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
|
2012-05-09 07:38:45 +08:00
|
|
|
TheTriple.setTriple(Triple::normalize(TripleName));
|
2011-01-20 14:39:06 +08:00
|
|
|
|
|
|
|
// Get the target specific parser.
|
|
|
|
std::string Error;
|
2012-05-09 07:38:45 +08:00
|
|
|
const Target *TheTarget = TargetRegistry::lookupTarget(ArchName, TheTriple,
|
|
|
|
Error);
|
2015-12-04 06:13:40 +08:00
|
|
|
if (!TheTarget)
|
|
|
|
report_fatal_error("can't find target: " + Error);
|
2012-05-09 07:38:45 +08:00
|
|
|
|
|
|
|
// Update the triple name and return the found target.
|
|
|
|
TripleName = TheTriple.getTriple();
|
|
|
|
return TheTarget;
|
2011-01-20 14:39:06 +08:00
|
|
|
}
|
|
|
|
|
2012-12-06 04:12:35 +08:00
|
|
|
bool llvm::RelocAddressLess(RelocationRef a, RelocationRef b) {
|
2015-07-06 23:47:43 +08:00
|
|
|
return a.getOffset() < b.getOffset();
|
2011-10-14 06:17:18 +08:00
|
|
|
}
|
|
|
|
|
2015-05-29 03:07:14 +08:00
|
|
|
namespace {
|
2016-08-16 03:49:24 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2016-08-26 03:41:08 +08:00
|
|
|
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));
|
|
|
|
}
|
|
|
|
|
2015-05-29 03:07:14 +08:00
|
|
|
class PrettyPrinter {
|
|
|
|
public:
|
2015-05-29 04:59:08 +08:00
|
|
|
virtual ~PrettyPrinter(){}
|
2015-05-29 22:44:13 +08:00
|
|
|
virtual void printInst(MCInstPrinter &IP, const MCInst *MI,
|
2015-05-29 03:07:14 +08:00
|
|
|
ArrayRef<uint8_t> Bytes, uint64_t Address,
|
|
|
|
raw_ostream &OS, StringRef Annot,
|
2016-08-16 03:49:24 +08:00
|
|
|
MCSubtargetInfo const &STI, SourcePrinter *SP) {
|
|
|
|
if (SP && (PrintSource || PrintLines))
|
|
|
|
SP->printSourceLine(OS, Address);
|
2016-03-19 00:26:48 +08:00
|
|
|
OS << format("%8" PRIx64 ":", Address);
|
2015-05-29 03:07:14 +08:00
|
|
|
if (!NoShowRawInsn) {
|
2016-03-19 00:26:48 +08:00
|
|
|
OS << "\t";
|
|
|
|
dumpBytes(Bytes, OS);
|
2015-05-29 03:07:14 +08:00
|
|
|
}
|
2016-03-19 00:26:48 +08:00
|
|
|
if (MI)
|
|
|
|
IP.printInst(MI, OS, "", STI);
|
|
|
|
else
|
|
|
|
OS << " <unknown>";
|
2015-05-29 03:07:14 +08:00
|
|
|
}
|
|
|
|
};
|
|
|
|
PrettyPrinter PrettyPrinterInst;
|
2015-05-29 22:44:13 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
}
|
2016-08-16 03:49:24 +08:00
|
|
|
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 {
|
2016-08-19 05:50:13 +08:00
|
|
|
if (SP && (PrintSource || PrintLines))
|
|
|
|
SP->printSourceLine(OS, Address, "");
|
2016-03-19 00:26:48 +08:00
|
|
|
if (!MI) {
|
|
|
|
printLead(Bytes, Address, OS);
|
|
|
|
OS << " <unknown>";
|
|
|
|
return;
|
|
|
|
}
|
2015-05-29 22:44:13 +08:00
|
|
|
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";
|
2016-08-19 05:50:13 +08:00
|
|
|
if (SP && (PrintSource || PrintLines))
|
|
|
|
SP->printSourceLine(OS, Address, "");
|
2015-05-29 22:44:13 +08:00
|
|
|
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;
|
2016-04-07 15:24:01 +08:00
|
|
|
|
|
|
|
class AMDGCNPrettyPrinter : public PrettyPrinter {
|
|
|
|
public:
|
2016-08-16 03:49:24 +08:00
|
|
|
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 {
|
2016-04-23 05:23:41 +08:00
|
|
|
if (!MI) {
|
|
|
|
OS << " <unknown>";
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2016-04-07 15:24:01 +08:00
|
|
|
SmallString<40> InstStr;
|
|
|
|
raw_svector_ostream IS(InstStr);
|
|
|
|
|
|
|
|
IP.printInst(MI, IS, "", STI);
|
|
|
|
|
2016-04-07 16:38:20 +08:00
|
|
|
OS << left_justify(IS.str(), 60) << format("// %012" PRIX64 ": ", Address);
|
2016-04-07 15:24:01 +08:00
|
|
|
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.
|
2016-04-07 16:38:20 +08:00
|
|
|
OS << format("%08" PRIX32 " ", static_cast<uint32_t>(D));
|
2016-04-07 15:24:01 +08:00
|
|
|
|
|
|
|
if (!Annot.empty())
|
|
|
|
OS << "// " << Annot;
|
|
|
|
}
|
|
|
|
};
|
|
|
|
AMDGCNPrettyPrinter AMDGCNPrettyPrinterInst;
|
|
|
|
|
2015-05-29 22:48:25 +08:00
|
|
|
PrettyPrinter &selectPrettyPrinter(Triple const &Triple) {
|
2015-05-29 22:44:13 +08:00
|
|
|
switch(Triple.getArch()) {
|
|
|
|
default:
|
|
|
|
return PrettyPrinterInst;
|
|
|
|
case Triple::hexagon:
|
|
|
|
return HexagonPrettyPrinterInst;
|
2016-04-07 15:24:01 +08:00
|
|
|
case Triple::amdgcn:
|
|
|
|
return AMDGCNPrettyPrinterInst;
|
2015-05-29 22:44:13 +08:00
|
|
|
}
|
2015-05-29 03:07:14 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-06-03 12:48:06 +08:00
|
|
|
template <class ELFT>
|
|
|
|
static std::error_code getRelocationValueString(const ELFObjectFile<ELFT> *Obj,
|
2015-08-11 04:50:40 +08:00
|
|
|
const RelocationRef &RelRef,
|
2015-06-03 12:48:06 +08:00
|
|
|
SmallVectorImpl<char> &Result) {
|
2015-08-11 04:50:40 +08:00
|
|
|
DataRefImpl Rel = RelRef.getRawDataRefImpl();
|
|
|
|
|
2015-06-03 12:48:06 +08:00
|
|
|
typedef typename ELFObjectFile<ELFT>::Elf_Sym Elf_Sym;
|
|
|
|
typedef typename ELFObjectFile<ELFT>::Elf_Shdr Elf_Shdr;
|
2015-07-02 22:21:38 +08:00
|
|
|
typedef typename ELFObjectFile<ELFT>::Elf_Rela Elf_Rela;
|
|
|
|
|
2015-06-03 12:48:06 +08:00
|
|
|
const ELFFile<ELFT> &EF = *Obj->getELFFile();
|
|
|
|
|
2015-07-01 20:56:27 +08:00
|
|
|
ErrorOr<const Elf_Shdr *> SecOrErr = EF.getSection(Rel.d.a);
|
|
|
|
if (std::error_code EC = SecOrErr.getError())
|
|
|
|
return EC;
|
|
|
|
const Elf_Shdr *Sec = *SecOrErr;
|
|
|
|
ErrorOr<const Elf_Shdr *> SymTabOrErr = EF.getSection(Sec->sh_link);
|
|
|
|
if (std::error_code EC = SymTabOrErr.getError())
|
|
|
|
return EC;
|
|
|
|
const Elf_Shdr *SymTab = *SymTabOrErr;
|
2015-06-29 20:38:31 +08:00
|
|
|
assert(SymTab->sh_type == ELF::SHT_SYMTAB ||
|
|
|
|
SymTab->sh_type == ELF::SHT_DYNSYM);
|
2015-07-01 20:56:27 +08:00
|
|
|
ErrorOr<const Elf_Shdr *> StrTabSec = EF.getSection(SymTab->sh_link);
|
|
|
|
if (std::error_code EC = StrTabSec.getError())
|
|
|
|
return EC;
|
|
|
|
ErrorOr<StringRef> StrTabOrErr = EF.getStringTable(*StrTabSec);
|
2015-06-29 22:39:25 +08:00
|
|
|
if (std::error_code EC = StrTabOrErr.getError())
|
|
|
|
return EC;
|
|
|
|
StringRef StrTab = *StrTabOrErr;
|
2015-08-11 04:50:40 +08:00
|
|
|
uint8_t type = RelRef.getType();
|
2015-06-03 12:48:06 +08:00
|
|
|
StringRef res;
|
|
|
|
int64_t addend = 0;
|
2015-07-01 20:56:27 +08:00
|
|
|
switch (Sec->sh_type) {
|
2015-06-03 12:48:06 +08:00
|
|
|
default:
|
|
|
|
return object_error::parse_failed;
|
|
|
|
case ELF::SHT_REL: {
|
|
|
|
// TODO: Read implicit addend from section data.
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
case ELF::SHT_RELA: {
|
2015-07-02 22:21:38 +08:00
|
|
|
const Elf_Rela *ERela = Obj->getRela(Rel);
|
|
|
|
addend = ERela->r_addend;
|
2015-06-03 12:48:06 +08:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
2015-08-11 04:50:40 +08:00
|
|
|
symbol_iterator SI = RelRef.getSymbol();
|
|
|
|
const Elf_Sym *symb = Obj->getSymbol(SI->getRawDataRefImpl());
|
2015-06-03 13:14:22 +08:00
|
|
|
StringRef Target;
|
|
|
|
if (symb->getType() == ELF::STT_SECTION) {
|
2016-05-03 04:28:12 +08:00
|
|
|
Expected<section_iterator> SymSI = SI->getSection();
|
|
|
|
if (!SymSI)
|
|
|
|
return errorToErrorCode(SymSI.takeError());
|
2015-08-11 04:50:40 +08:00
|
|
|
const Elf_Shdr *SymSec = Obj->getSection((*SymSI)->getRawDataRefImpl());
|
|
|
|
ErrorOr<StringRef> SecName = EF.getSectionName(SymSec);
|
2015-06-03 13:14:22 +08:00
|
|
|
if (std::error_code EC = SecName.getError())
|
|
|
|
return EC;
|
|
|
|
Target = *SecName;
|
|
|
|
} else {
|
2016-04-21 05:24:34 +08:00
|
|
|
Expected<StringRef> SymName = symb->getName(StrTab);
|
2015-06-03 13:14:22 +08:00
|
|
|
if (!SymName)
|
2016-04-21 05:24:34 +08:00
|
|
|
return errorToErrorCode(SymName.takeError());
|
2015-06-03 13:14:22 +08:00
|
|
|
Target = *SymName;
|
|
|
|
}
|
2015-06-03 12:48:06 +08:00
|
|
|
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);
|
2015-06-03 13:14:22 +08:00
|
|
|
fmt << Target << (addend < 0 ? "" : "+") << addend << "-P";
|
2015-06-03 12:48:06 +08:00
|
|
|
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);
|
2015-06-03 13:14:22 +08:00
|
|
|
fmt << Target << (addend < 0 ? "" : "+") << addend;
|
2015-06-03 12:48:06 +08:00
|
|
|
fmt.flush();
|
|
|
|
Result.append(fmtbuf.begin(), fmtbuf.end());
|
|
|
|
} break;
|
|
|
|
default:
|
|
|
|
res = "Unknown";
|
|
|
|
}
|
|
|
|
break;
|
2016-03-02 05:21:42 +08:00
|
|
|
case ELF::EM_LANAI:
|
2015-06-03 12:48:06 +08:00
|
|
|
case ELF::EM_AARCH64: {
|
|
|
|
std::string fmtbuf;
|
|
|
|
raw_string_ostream fmt(fmtbuf);
|
2015-06-03 13:14:22 +08:00
|
|
|
fmt << Target;
|
2015-06-03 12:48:06 +08:00
|
|
|
if (addend != 0)
|
|
|
|
fmt << (addend < 0 ? "" : "+") << addend;
|
|
|
|
fmt.flush();
|
|
|
|
Result.append(fmtbuf.begin(), fmtbuf.end());
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
case ELF::EM_386:
|
2015-11-04 19:21:50 +08:00
|
|
|
case ELF::EM_IAMCU:
|
2015-06-03 12:48:06 +08:00
|
|
|
case ELF::EM_ARM:
|
|
|
|
case ELF::EM_HEXAGON:
|
|
|
|
case ELF::EM_MIPS:
|
2016-07-16 06:27:55 +08:00
|
|
|
case ELF::EM_BPF:
|
2015-06-03 13:14:22 +08:00
|
|
|
res = Target;
|
2015-06-03 12:48:06 +08:00
|
|
|
break;
|
2016-01-13 04:56:01 +08:00
|
|
|
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;
|
2015-06-03 12:48:06 +08:00
|
|
|
default:
|
|
|
|
res = "Unknown";
|
|
|
|
}
|
|
|
|
if (Result.empty())
|
|
|
|
Result.append(res.begin(), res.end());
|
2015-06-09 23:20:42 +08:00
|
|
|
return std::error_code();
|
2015-06-03 12:48:06 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static std::error_code getRelocationValueString(const ELFObjectFileBase *Obj,
|
2015-08-11 04:50:40 +08:00
|
|
|
const RelocationRef &Rel,
|
2015-06-03 12:48:06 +08:00
|
|
|
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();
|
2016-04-21 05:24:34 +08:00
|
|
|
Expected<StringRef> SymNameOrErr = SymI->getName();
|
|
|
|
if (!SymNameOrErr)
|
|
|
|
return errorToErrorCode(SymNameOrErr.takeError());
|
2015-07-03 04:55:21 +08:00
|
|
|
StringRef SymName = *SymNameOrErr;
|
2015-06-03 12:48:06 +08:00
|
|
|
Result.append(SymName.begin(), SymName.end());
|
2015-06-09 23:20:42 +08:00
|
|
|
return std::error_code();
|
2015-06-03 12:48:06 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
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;
|
2016-06-25 02:24:42 +08:00
|
|
|
Expected<uint64_t> Addr = Symbol.getAddress();
|
|
|
|
if (!Addr) {
|
|
|
|
std::string Buf;
|
|
|
|
raw_string_ostream OS(Buf);
|
|
|
|
logAllUnhandledErrors(Addr.takeError(), OS, "");
|
|
|
|
OS.flush();
|
|
|
|
report_fatal_error(Buf);
|
|
|
|
}
|
2015-07-04 02:19:00 +08:00
|
|
|
if (*Addr != Val)
|
2015-06-03 12:48:06 +08:00
|
|
|
continue;
|
2016-04-21 05:24:34 +08:00
|
|
|
Expected<StringRef> Name = Symbol.getName();
|
|
|
|
if (!Name) {
|
|
|
|
std::string Buf;
|
|
|
|
raw_string_ostream OS(Buf);
|
|
|
|
logAllUnhandledErrors(Name.takeError(), OS, "");
|
|
|
|
OS.flush();
|
|
|
|
report_fatal_error(Buf);
|
|
|
|
}
|
2015-07-03 04:55:21 +08:00
|
|
|
fmt << *Name;
|
2015-06-03 12:48:06 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
// If we couldn't find a symbol that this relocation refers to, try
|
|
|
|
// to find a section beginning instead.
|
2015-07-29 23:45:39 +08:00
|
|
|
for (const SectionRef &Section : ToolSectionFilter(*O)) {
|
2015-06-03 12:48:06 +08:00
|
|
|
std::error_code ec;
|
|
|
|
|
|
|
|
StringRef Name;
|
|
|
|
uint64_t Addr = Section.getAddress();
|
|
|
|
if (Addr != Val)
|
|
|
|
continue;
|
|
|
|
if ((ec = Section.getName(Name)))
|
|
|
|
report_fatal_error(ec.message());
|
|
|
|
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);
|
2016-04-21 05:24:34 +08:00
|
|
|
Expected<StringRef> SOrErr = SI->getName();
|
|
|
|
error(errorToErrorCode(SOrErr.takeError()));
|
2015-08-05 15:18:31 +08:00
|
|
|
S = *SOrErr;
|
2015-06-03 12:48:06 +08:00
|
|
|
} 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_fatal_error("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
|
2015-06-09 23:20:42 +08:00
|
|
|
return std::error_code();
|
2015-06-03 12:48:06 +08:00
|
|
|
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_fatal_error("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_fatal_error("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_fatal_error("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());
|
2015-06-09 23:20:42 +08:00
|
|
|
return std::error_code();
|
2015-06-03 12:48:06 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static std::error_code getRelocationValueString(const RelocationRef &Rel,
|
|
|
|
SmallVectorImpl<char> &Result) {
|
2015-06-26 22:51:16 +08:00
|
|
|
const ObjectFile *Obj = Rel.getObject();
|
2015-06-03 12:48:06 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2015-06-30 11:41:26 +08:00
|
|
|
/// @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;
|
|
|
|
}
|
|
|
|
|
2016-08-17 18:17:57 +08:00
|
|
|
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");
|
|
|
|
}
|
|
|
|
|
2011-10-14 06:17:18 +08:00
|
|
|
static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) {
|
2016-09-13 01:08:22 +08:00
|
|
|
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
|
|
|
|
2012-08-29 03:24:49 +08:00
|
|
|
// Package up features to be passed to target/subtarget
|
2016-06-16 17:17:03 +08:00
|
|
|
SubtargetFeatures Features = Obj->getFeatures();
|
2012-08-29 03:24:49 +08:00
|
|
|
if (MAttrs.size()) {
|
|
|
|
for (unsigned i = 0; i != MAttrs.size(); ++i)
|
|
|
|
Features.AddFeature(MAttrs[i]);
|
|
|
|
}
|
|
|
|
|
2014-03-06 13:51:42 +08:00
|
|
|
std::unique_ptr<const MCRegisterInfo> MRI(
|
|
|
|
TheTarget->createMCRegInfo(TripleName));
|
2015-12-17 09:59:50 +08:00
|
|
|
if (!MRI)
|
|
|
|
report_fatal_error("error: no register info for target " + TripleName);
|
2013-05-17 05:28:23 +08:00
|
|
|
|
|
|
|
// Set up disassembler.
|
2014-03-06 13:51:42 +08:00
|
|
|
std::unique_ptr<const MCAsmInfo> AsmInfo(
|
|
|
|
TheTarget->createMCAsmInfo(*MRI, TripleName));
|
2015-12-17 09:59:50 +08:00
|
|
|
if (!AsmInfo)
|
|
|
|
report_fatal_error("error: no assembly info for target " + TripleName);
|
2014-03-06 13:51:42 +08:00
|
|
|
std::unique_ptr<const MCSubtargetInfo> STI(
|
2016-06-16 17:17:03 +08:00
|
|
|
TheTarget->createMCSubtargetInfo(TripleName, MCPU, Features.getString()));
|
2015-12-17 09:59:50 +08:00
|
|
|
if (!STI)
|
|
|
|
report_fatal_error("error: no subtarget info for target " + TripleName);
|
2014-03-06 13:51:42 +08:00
|
|
|
std::unique_ptr<const MCInstrInfo> MII(TheTarget->createMCInstrInfo());
|
2015-12-17 09:59:50 +08:00
|
|
|
if (!MII)
|
|
|
|
report_fatal_error("error: no instruction info for target " + TripleName);
|
2014-04-15 12:40:56 +08:00
|
|
|
std::unique_ptr<const MCObjectFileInfo> MOFI(new MCObjectFileInfo);
|
|
|
|
MCContext Ctx(AsmInfo.get(), MRI.get(), MOFI.get());
|
|
|
|
|
|
|
|
std::unique_ptr<MCDisassembler> DisAsm(
|
|
|
|
TheTarget->createMCDisassembler(*STI, Ctx));
|
2015-12-17 09:59:50 +08:00
|
|
|
if (!DisAsm)
|
|
|
|
report_fatal_error("error: no disassembler for target " + TripleName);
|
2013-05-17 05:28:23 +08:00
|
|
|
|
2014-03-06 13:51:42 +08:00
|
|
|
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
|
|
|
|
2013-05-17 05:28:23 +08:00
|
|
|
int AsmPrinterVariant = AsmInfo->getAssemblerDialect();
|
2015-09-16 00:17:27 +08:00
|
|
|
std::unique_ptr<MCInstPrinter> IP(TheTarget->createMCInstPrinter(
|
|
|
|
Triple(TripleName), AsmPrinterVariant, *AsmInfo, *MII, *MRI));
|
2015-12-17 09:59:50 +08:00
|
|
|
if (!IP)
|
|
|
|
report_fatal_error("error: no instruction printer for target " +
|
|
|
|
TripleName);
|
2015-06-08 05:07:17 +08:00
|
|
|
IP->setPrintImmHex(PrintImmHex);
|
2015-05-29 22:48:25 +08:00
|
|
|
PrettyPrinter &PIP = selectPrettyPrinter(Triple(TripleName));
|
2013-05-17 05:28:23 +08:00
|
|
|
|
2014-03-21 06:55:15 +08:00
|
|
|
StringRef Fmt = Obj->getBytesInAddress() > 4 ? "\t\t%016" PRIx64 ": " :
|
|
|
|
"\t\t\t%08" PRIx64 ": ";
|
|
|
|
|
2016-08-16 03:49:24 +08:00
|
|
|
SourcePrinter SP(Obj, TheTarget->getName());
|
|
|
|
|
2014-01-26 01:38:19 +08:00
|
|
|
// Create a mapping, RelocSecs = SectionRelocMap[S], where sections
|
|
|
|
// in RelocSecs contain the relocations for section S.
|
2014-06-13 11:07:50 +08:00
|
|
|
std::error_code EC;
|
2014-03-13 22:37:36 +08:00
|
|
|
std::map<SectionRef, SmallVector<SectionRef, 1>> SectionRelocMap;
|
2015-07-29 23:45:39 +08:00
|
|
|
for (const SectionRef &Section : ToolSectionFilter(*Obj)) {
|
2014-03-13 22:37:36 +08:00
|
|
|
section_iterator Sec2 = Section.getRelocatedSection();
|
2014-02-11 04:24:04 +08:00
|
|
|
if (Sec2 != Obj->section_end())
|
2014-03-13 22:37:36 +08:00
|
|
|
SectionRelocMap[*Sec2].push_back(Section);
|
2014-01-26 01:38:19 +08:00
|
|
|
}
|
|
|
|
|
2015-07-08 06:06:59 +08:00
|
|
|
// Create a mapping from virtual address to symbol name. This is used to
|
2015-11-18 10:49:19 +08:00
|
|
|
// pretty print the symbols while disassembling.
|
2016-08-17 18:17:57 +08:00
|
|
|
typedef std::vector<std::tuple<uint64_t, StringRef, uint8_t>> SectionSymbolsTy;
|
2015-11-18 10:49:19 +08:00
|
|
|
std::map<SectionRef, SectionSymbolsTy> AllSymbols;
|
|
|
|
for (const SymbolRef &Symbol : Obj->symbols()) {
|
2016-06-25 02:24:42 +08:00
|
|
|
Expected<uint64_t> AddressOrErr = Symbol.getAddress();
|
|
|
|
error(errorToErrorCode(AddressOrErr.takeError()));
|
2015-11-18 10:49:19 +08:00
|
|
|
uint64_t Address = *AddressOrErr;
|
|
|
|
|
2016-04-21 05:24:34 +08:00
|
|
|
Expected<StringRef> Name = Symbol.getName();
|
|
|
|
error(errorToErrorCode(Name.takeError()));
|
2015-11-18 10:49:19 +08:00
|
|
|
if (Name->empty())
|
|
|
|
continue;
|
2015-07-10 02:11:40 +08:00
|
|
|
|
2016-05-03 04:28:12 +08:00
|
|
|
Expected<section_iterator> SectionOrErr = Symbol.getSection();
|
|
|
|
error(errorToErrorCode(SectionOrErr.takeError()));
|
2015-11-18 10:49:19 +08:00
|
|
|
section_iterator SecI = *SectionOrErr;
|
|
|
|
if (SecI == Obj->section_end())
|
|
|
|
continue;
|
2016-08-26 03:41:08 +08:00
|
|
|
|
2016-08-17 18:17:57 +08:00
|
|
|
uint8_t SymbolType = ELF::STT_NOTYPE;
|
2016-08-26 03:41:08 +08:00
|
|
|
if (Obj->isELF())
|
2016-08-17 18:17:57 +08:00
|
|
|
SymbolType = getElfSymbolType(Obj, Symbol);
|
|
|
|
|
|
|
|
AllSymbols[*SecI].emplace_back(Address, *Name, SymbolType);
|
2015-07-08 06:06:59 +08:00
|
|
|
|
2015-11-18 10:49:19 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// 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())
|
2015-07-08 06:06:59 +08:00
|
|
|
continue;
|
2015-11-18 10:49:19 +08:00
|
|
|
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();
|
2015-07-08 06:06:59 +08:00
|
|
|
|
2015-11-18 10:49:19 +08:00
|
|
|
if (Sec != SectionAddresses.end())
|
2016-08-17 18:17:57 +08:00
|
|
|
AllSymbols[Sec->second].emplace_back(VA, Name, ELF::STT_NOTYPE);
|
2015-11-18 10:49:19 +08:00
|
|
|
}
|
2015-07-08 06:06:59 +08:00
|
|
|
}
|
|
|
|
|
2015-11-18 10:49:19 +08:00
|
|
|
// 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());
|
|
|
|
|
2015-07-29 23:45:39 +08:00
|
|
|
for (const SectionRef &Section : ToolSectionFilter(*Obj)) {
|
2015-07-24 04:58:49 +08:00
|
|
|
if (!DisassembleAll && (!Section.isText() || Section.isVirtual()))
|
2014-01-25 08:32:01 +08:00
|
|
|
continue;
|
2011-06-26 01:55:23 +08:00
|
|
|
|
2014-10-08 23:28:58 +08:00
|
|
|
uint64_t SectionAddr = Section.getAddress();
|
|
|
|
uint64_t SectSize = Section.getSize();
|
2014-11-11 17:58:25 +08:00
|
|
|
if (!SectSize)
|
|
|
|
continue;
|
2014-02-25 06:12:11 +08:00
|
|
|
|
2015-11-18 10:49:19 +08:00
|
|
|
// Get the list of all the symbols in this section.
|
|
|
|
SectionSymbolsTy &Symbols = AllSymbols[Section];
|
2015-10-02 05:57:09 +08:00
|
|
|
std::vector<uint64_t> DataMappingSymsAddr;
|
|
|
|
std::vector<uint64_t> TextMappingSymsAddr;
|
2016-08-26 03:41:08 +08:00
|
|
|
if (isArmElf(Obj)) {
|
2015-11-18 10:49:19 +08:00
|
|
|
for (const auto &Symb : Symbols) {
|
2016-08-17 18:17:57 +08:00
|
|
|
uint64_t Address = std::get<0>(Symb);
|
|
|
|
StringRef Name = std::get<1>(Symb);
|
2015-11-18 10:49:19 +08:00
|
|
|
if (Name.startswith("$d"))
|
2015-11-18 12:35:32 +08:00
|
|
|
DataMappingSymsAddr.push_back(Address - SectionAddr);
|
2015-11-18 10:49:19 +08:00
|
|
|
if (Name.startswith("$x"))
|
2015-11-18 12:35:32 +08:00
|
|
|
TextMappingSymsAddr.push_back(Address - SectionAddr);
|
2016-08-26 03:41:08 +08:00
|
|
|
if (Name.startswith("$a"))
|
|
|
|
TextMappingSymsAddr.push_back(Address - SectionAddr);
|
|
|
|
if (Name.startswith("$t"))
|
|
|
|
TextMappingSymsAddr.push_back(Address - SectionAddr);
|
2011-07-16 02:39:24 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-10-02 05:57:09 +08:00
|
|
|
std::sort(DataMappingSymsAddr.begin(), DataMappingSymsAddr.end());
|
|
|
|
std::sort(TextMappingSymsAddr.begin(), TextMappingSymsAddr.end());
|
2011-07-16 02:39:24 +08:00
|
|
|
|
2011-10-14 06:17:18 +08:00
|
|
|
// Make a list of all the relocations for this section.
|
|
|
|
std::vector<RelocationRef> Rels;
|
|
|
|
if (InlineRelocs) {
|
2014-03-14 22:22:49 +08:00
|
|
|
for (const SectionRef &RelocSec : SectionRelocMap[Section]) {
|
|
|
|
for (const RelocationRef &Reloc : RelocSec.relocations()) {
|
|
|
|
Rels.push_back(Reloc);
|
|
|
|
}
|
2011-10-14 06:17:18 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Sort relocations by address.
|
|
|
|
std::sort(Rels.begin(), Rels.end(), RelocAddressLess);
|
|
|
|
|
Add a function to get the segment name of a section.
On MachO, sections also have segment names. When a tool looking at a .o file
prints a segment name, this is what they mean. In reality, a .o has only one
anonymous, segment.
This patch adds a MachO only function to fetch that segment name. I named it
getSectionFinalSegmentName since the main use for the name seems to be inform
the linker with segment this section should go to.
The patch also changes MachOObjectFile::getSectionName to return just the
section name instead of computing SegmentName,SectionName.
The main difference from the previous patch is that it doesn't use
InMemoryStruct. It is extremely dangerous: if the endians match it returns
a pointer to the file buffer, if not, it returns a pointer to an internal buffer
that is overwritten in the next API call.
We should change all of this code to use
support::detail::packed_endian_specific_integral like ELF, but since these
functions only handle strings, they work with big and little endian machines
as is.
I have tested this by installing ubuntu 12.10 ppc on qemu, that is why it took
so long :-)
llvm-svn: 170838
2012-12-21 11:47:03 +08:00
|
|
|
StringRef SegmentName = "";
|
2014-01-25 08:32:01 +08:00
|
|
|
if (const MachOObjectFile *MachO = dyn_cast<const MachOObjectFile>(Obj)) {
|
2014-03-13 22:37:36 +08:00
|
|
|
DataRefImpl DR = Section.getRawDataRefImpl();
|
2013-04-19 02:08:55 +08:00
|
|
|
SegmentName = MachO->getSectionFinalSegmentName(DR);
|
Add a function to get the segment name of a section.
On MachO, sections also have segment names. When a tool looking at a .o file
prints a segment name, this is what they mean. In reality, a .o has only one
anonymous, segment.
This patch adds a MachO only function to fetch that segment name. I named it
getSectionFinalSegmentName since the main use for the name seems to be inform
the linker with segment this section should go to.
The patch also changes MachOObjectFile::getSectionName to return just the
section name instead of computing SegmentName,SectionName.
The main difference from the previous patch is that it doesn't use
InMemoryStruct. It is extremely dangerous: if the endians match it returns
a pointer to the file buffer, if not, it returns a pointer to an internal buffer
that is overwritten in the next API call.
We should change all of this code to use
support::detail::packed_endian_specific_integral like ELF, but since these
functions only handle strings, they work with big and little endian machines
as is.
I have tested this by installing ubuntu 12.10 ppc on qemu, that is why it took
so long :-)
llvm-svn: 170838
2012-12-21 11:47:03 +08:00
|
|
|
}
|
2011-06-26 01:55:23 +08:00
|
|
|
StringRef name;
|
2015-08-05 15:18:31 +08:00
|
|
|
error(Section.getName(name));
|
2016-09-13 01:08:22 +08:00
|
|
|
|
|
|
|
if ((SectionAddr <= StopAddress) &&
|
|
|
|
(SectionAddr + SectSize) >= StartAddress) {
|
Add a function to get the segment name of a section.
On MachO, sections also have segment names. When a tool looking at a .o file
prints a segment name, this is what they mean. In reality, a .o has only one
anonymous, segment.
This patch adds a MachO only function to fetch that segment name. I named it
getSectionFinalSegmentName since the main use for the name seems to be inform
the linker with segment this section should go to.
The patch also changes MachOObjectFile::getSectionName to return just the
section name instead of computing SegmentName,SectionName.
The main difference from the previous patch is that it doesn't use
InMemoryStruct. It is extremely dangerous: if the endians match it returns
a pointer to the file buffer, if not, it returns a pointer to an internal buffer
that is overwritten in the next API call.
We should change all of this code to use
support::detail::packed_endian_specific_integral like ELF, but since these
functions only handle strings, they work with big and little endian machines
as is.
I have tested this by installing ubuntu 12.10 ppc on qemu, that is why it took
so long :-)
llvm-svn: 170838
2012-12-21 11:47:03 +08:00
|
|
|
outs() << "Disassembly of section ";
|
|
|
|
if (!SegmentName.empty())
|
|
|
|
outs() << SegmentName << ",";
|
|
|
|
outs() << name << ':';
|
2016-09-13 01:08:22 +08:00
|
|
|
}
|
2011-07-16 02:39:24 +08:00
|
|
|
|
2015-06-04 23:01:05 +08:00
|
|
|
// If the section has no symbol at the start, just insert a dummy one.
|
2016-08-17 18:17:57 +08:00
|
|
|
if (Symbols.empty() || std::get<0>(Symbols[0]) != 0) {
|
2016-08-26 03:41:08 +08:00
|
|
|
Symbols.insert(Symbols.begin(),
|
|
|
|
std::make_tuple(SectionAddr, name, Section.isText()
|
|
|
|
? ELF::STT_FUNC
|
|
|
|
: ELF::STT_OBJECT));
|
2016-08-17 18:17:57 +08:00
|
|
|
}
|
2014-06-27 06:52:05 +08:00
|
|
|
|
|
|
|
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
|
|
|
|
2014-11-12 10:04:27 +08:00
|
|
|
StringRef BytesStr;
|
2015-08-05 15:18:31 +08:00
|
|
|
error(Section.getContents(BytesStr));
|
2014-11-12 22:01:17 +08:00
|
|
|
ArrayRef<uint8_t> Bytes(reinterpret_cast<const uint8_t *>(BytesStr.data()),
|
|
|
|
BytesStr.size());
|
2014-11-12 10:04:27 +08:00
|
|
|
|
2011-01-20 14:39:06 +08:00
|
|
|
uint64_t Size;
|
|
|
|
uint64_t Index;
|
2011-07-16 02:39:24 +08:00
|
|
|
|
2011-10-14 06:17:18 +08:00
|
|
|
std::vector<RelocationRef>::const_iterator rel_cur = Rels.begin();
|
|
|
|
std::vector<RelocationRef>::const_iterator rel_end = Rels.end();
|
2011-07-16 02:39:24 +08:00
|
|
|
// Disassemble symbol by symbol.
|
|
|
|
for (unsigned si = 0, se = Symbols.size(); si != se; ++si) {
|
2016-08-17 18:17:57 +08:00
|
|
|
uint64_t Start = std::get<0>(Symbols[si]) - SectionAddr;
|
2015-11-18 10:49:19 +08:00
|
|
|
// The end is either the section end or the beginning of the next
|
|
|
|
// symbol.
|
|
|
|
uint64_t End =
|
2016-08-17 18:17:57 +08:00
|
|
|
(si == se - 1) ? SectSize : std::get<0>(Symbols[si + 1]) - SectionAddr;
|
2015-11-18 10:49:19 +08:00
|
|
|
// Don't try to disassemble beyond the end of section contents.
|
|
|
|
if (End > SectSize)
|
|
|
|
End = SectSize;
|
2014-08-18 00:31:39 +08:00
|
|
|
// If this symbol has the same address as the next symbol, then skip it.
|
2015-11-18 10:49:19 +08:00
|
|
|
if (Start >= End)
|
2011-10-14 04:37:08 +08:00
|
|
|
continue;
|
|
|
|
|
2016-09-13 01:08:22 +08:00
|
|
|
// 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;
|
|
|
|
|
2016-04-07 15:24:01 +08:00
|
|
|
if (Obj->isELF() && Obj->getArch() == Triple::amdgcn) {
|
|
|
|
// make size 4 bytes folded
|
|
|
|
End = Start + ((End - Start) & ~0x3ull);
|
2016-08-17 18:17:57 +08:00
|
|
|
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;
|
|
|
|
}
|
2016-04-07 15:24:01 +08:00
|
|
|
}
|
|
|
|
|
2016-08-17 18:17:57 +08:00
|
|
|
outs() << '\n' << std::get<1>(Symbols[si]) << ":\n";
|
2011-07-16 02:39:24 +08:00
|
|
|
|
|
|
|
#ifndef NDEBUG
|
2014-01-25 08:32:01 +08:00
|
|
|
raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls();
|
2011-07-16 02:39:24 +08:00
|
|
|
#else
|
2014-01-25 08:32:01 +08:00
|
|
|
raw_ostream &DebugOut = nulls();
|
2011-07-16 02:39:24 +08:00
|
|
|
#endif
|
|
|
|
|
2011-09-20 01:56:04 +08:00
|
|
|
for (Index = Start; Index < End; Index += Size) {
|
|
|
|
MCInst Inst;
|
|
|
|
|
2016-09-13 01:08:22 +08:00
|
|
|
if (Index + SectionAddr < StartAddress ||
|
|
|
|
Index + SectionAddr > StopAddress) {
|
|
|
|
// skip byte by byte till StartAddress is reached
|
|
|
|
Size = 1;
|
|
|
|
continue;
|
|
|
|
}
|
2015-10-02 05:57:09 +08:00
|
|
|
// AArch64 ELF binaries can interleave data and text in the
|
|
|
|
// same section. We rely on the markers introduced to
|
2016-08-26 03:41:08 +08:00
|
|
|
// 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) {
|
2015-10-02 05:57:09 +08:00
|
|
|
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());
|
2016-08-26 03:41:08 +08:00
|
|
|
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);
|
2015-10-02 05:57:09 +08:00
|
|
|
} else if (Index + 2 <= End) {
|
|
|
|
Stride = 2;
|
|
|
|
dumpBytes(Bytes.slice(Index, 2), outs());
|
2016-08-26 03:41:08 +08:00
|
|
|
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);
|
2015-10-02 05:57:09 +08:00
|
|
|
} else {
|
|
|
|
Stride = 1;
|
|
|
|
dumpBytes(Bytes.slice(Index, 1), outs());
|
2016-08-26 03:41:08 +08:00
|
|
|
outs() << "\t\t.byte\t";
|
|
|
|
outs() << "0x" << format("%02" PRIx8, Bytes.slice(Index, 1)[0]);
|
2015-10-02 05:57:09 +08:00
|
|
|
}
|
|
|
|
Index += Stride;
|
|
|
|
outs() << "\n";
|
|
|
|
auto TAI = std::lower_bound(TextMappingSymsAddr.begin(),
|
|
|
|
TextMappingSymsAddr.end(), Index);
|
|
|
|
if (TAI != TextMappingSymsAddr.end() && *TAI == Index)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-08-26 03:41:08 +08:00
|
|
|
// 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) {
|
2016-09-13 01:08:22 +08:00
|
|
|
if (((SectionAddr + Index) < StartAddress) ||
|
|
|
|
((SectionAddr + Index) > StopAddress))
|
|
|
|
continue;
|
2016-08-26 03:41:08 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2015-10-02 05:57:09 +08:00
|
|
|
if (Index >= End)
|
|
|
|
break;
|
|
|
|
|
2016-08-26 03:41:08 +08:00
|
|
|
// Disassemble a real instruction or a data when disassemble all is
|
|
|
|
// provided
|
2016-03-19 00:26:48 +08:00
|
|
|
bool Disassembled = DisAsm->getInstruction(Inst, Size, Bytes.slice(Index),
|
|
|
|
SectionAddr + Index, DebugOut,
|
|
|
|
CommentStream);
|
|
|
|
if (Size == 0)
|
|
|
|
Size = 1;
|
2016-08-16 03:49:24 +08:00
|
|
|
|
2016-03-19 00:26:48 +08:00
|
|
|
PIP.printInst(*IP, Disassembled ? &Inst : nullptr,
|
2016-08-16 03:49:24 +08:00
|
|
|
Bytes.slice(Index, Size), SectionAddr + Index, outs(), "",
|
|
|
|
*STI, &SP);
|
2016-03-19 00:26:48 +08:00
|
|
|
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;
|
2015-11-18 10:49:19 +08:00
|
|
|
}
|
2016-03-19 00:26:48 +08:00
|
|
|
}
|
2015-11-18 10:49:19 +08:00
|
|
|
|
2016-03-19 00:26:48 +08:00
|
|
|
// 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,
|
2016-08-17 18:17:57 +08:00
|
|
|
const std::tuple<uint64_t, StringRef, uint8_t> &RHS) {
|
|
|
|
return LHS < std::get<0>(RHS);
|
2016-03-19 00:26:48 +08:00
|
|
|
});
|
|
|
|
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() << '>';
|
2015-07-08 06:06:59 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2011-07-21 03:37:35 +08:00
|
|
|
}
|
2016-03-19 00:26:48 +08:00
|
|
|
outs() << "\n";
|
2011-10-14 06:17:18 +08:00
|
|
|
|
|
|
|
// Print relocation for instruction.
|
|
|
|
while (rel_cur != rel_end) {
|
2015-06-30 11:41:26 +08:00
|
|
|
bool hidden = getHidden(*rel_cur);
|
2015-06-30 07:29:12 +08:00
|
|
|
uint64_t addr = rel_cur->getOffset();
|
2011-10-14 06:17:18 +08:00
|
|
|
SmallString<16> name;
|
|
|
|
SmallString<32> val;
|
2011-10-26 04:35:53 +08:00
|
|
|
|
|
|
|
// If this relocation is hidden, skip it.
|
2016-09-13 01:08:22 +08:00
|
|
|
if (hidden || ((SectionAddr + addr) < StartAddress)) {
|
|
|
|
++rel_cur;
|
|
|
|
continue;
|
|
|
|
}
|
2011-10-26 04:35:53 +08:00
|
|
|
|
2011-10-14 06:17:18 +08:00
|
|
|
// Stop when rel_cur's address is past the current instruction.
|
2011-10-26 04:15:39 +08:00
|
|
|
if (addr >= Index + Size) break;
|
2015-06-30 12:08:37 +08:00
|
|
|
rel_cur->getTypeName(name);
|
2015-08-05 15:18:31 +08:00
|
|
|
error(getRelocationValueString(*rel_cur, val));
|
2014-03-21 06:55:15 +08:00
|
|
|
outs() << format(Fmt.data(), SectionAddr + addr) << name
|
2012-03-10 10:04:38 +08:00
|
|
|
<< "\t" << val << "\n";
|
2011-10-14 06:17:18 +08:00
|
|
|
++rel_cur;
|
|
|
|
}
|
2011-07-21 03:37:35 +08:00
|
|
|
}
|
2011-01-20 14:39:06 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-01-21 05:47:46 +08:00
|
|
|
void llvm::PrintRelocations(const ObjectFile *Obj) {
|
2014-03-21 06:55:15 +08:00
|
|
|
StringRef Fmt = Obj->getBytesInAddress() > 4 ? "%016" PRIx64 :
|
|
|
|
"%08" PRIx64;
|
2016-03-22 04:59:15 +08:00
|
|
|
// Regular objdump doesn't print relocations in non-relocatable object
|
|
|
|
// files.
|
|
|
|
if (!Obj->isRelocatableObject())
|
|
|
|
return;
|
2014-08-18 03:09:37 +08:00
|
|
|
|
2015-07-29 23:45:39 +08:00
|
|
|
for (const SectionRef &Section : ToolSectionFilter(*Obj)) {
|
2014-03-13 22:37:36 +08:00
|
|
|
if (Section.relocation_begin() == Section.relocation_end())
|
2011-10-08 08:18:30 +08:00
|
|
|
continue;
|
|
|
|
StringRef secname;
|
2015-08-05 15:18:31 +08:00
|
|
|
error(Section.getName(secname));
|
2011-10-08 08:18:30 +08:00
|
|
|
outs() << "RELOCATION RECORDS FOR [" << secname << "]:\n";
|
2014-03-14 22:22:49 +08:00
|
|
|
for (const RelocationRef &Reloc : Section.relocations()) {
|
2015-06-30 11:41:26 +08:00
|
|
|
bool hidden = getHidden(Reloc);
|
2015-06-30 07:29:12 +08:00
|
|
|
uint64_t address = Reloc.getOffset();
|
2011-10-08 08:18:30 +08:00
|
|
|
SmallString<32> relocname;
|
|
|
|
SmallString<32> valuestr;
|
2016-09-13 01:08:22 +08:00
|
|
|
if (address < StartAddress || address > StopAddress || hidden)
|
2014-03-14 22:22:49 +08:00
|
|
|
continue;
|
2015-06-30 12:08:37 +08:00
|
|
|
Reloc.getTypeName(relocname);
|
2015-08-05 15:18:31 +08:00
|
|
|
error(getRelocationValueString(Reloc, valuestr));
|
2014-03-21 06:55:15 +08:00
|
|
|
outs() << format(Fmt.data(), address) << " " << relocname << " "
|
|
|
|
<< valuestr << "\n";
|
2011-10-08 08:18:30 +08:00
|
|
|
}
|
|
|
|
outs() << "\n";
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-01-21 05:47:46 +08:00
|
|
|
void llvm::PrintSectionHeaders(const ObjectFile *Obj) {
|
2011-10-11 05:21:34 +08:00
|
|
|
outs() << "Sections:\n"
|
|
|
|
"Idx Name Size Address Type\n";
|
|
|
|
unsigned i = 0;
|
2015-07-29 23:45:39 +08:00
|
|
|
for (const SectionRef &Section : ToolSectionFilter(*Obj)) {
|
2011-10-11 05:21:34 +08:00
|
|
|
StringRef Name;
|
2015-08-05 15:18:31 +08:00
|
|
|
error(Section.getName(Name));
|
2014-10-08 23:28:58 +08:00
|
|
|
uint64_t Address = Section.getAddress();
|
|
|
|
uint64_t Size = Section.getSize();
|
|
|
|
bool Text = Section.isText();
|
|
|
|
bool Data = Section.isData();
|
|
|
|
bool BSS = Section.isBSS();
|
2011-10-11 05:21:34 +08:00
|
|
|
std::string Type = (std::string(Text ? "TEXT " : "") +
|
2011-10-14 04:37:20 +08:00
|
|
|
(Data ? "DATA " : "") + (BSS ? "BSS" : ""));
|
2014-03-13 22:37:36 +08:00
|
|
|
outs() << format("%3d %-13s %08" PRIx64 " %016" PRIx64 " %s\n", i,
|
|
|
|
Name.str().c_str(), Size, Address, Type.c_str());
|
2011-10-11 05:21:34 +08:00
|
|
|
++i;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-01-21 05:47:46 +08:00
|
|
|
void llvm::PrintSectionContents(const ObjectFile *Obj) {
|
2014-06-13 11:07:50 +08:00
|
|
|
std::error_code EC;
|
2015-07-29 23:45:39 +08:00
|
|
|
for (const SectionRef &Section : ToolSectionFilter(*Obj)) {
|
2011-10-18 01:13:22 +08:00
|
|
|
StringRef Name;
|
|
|
|
StringRef Contents;
|
2015-08-05 15:18:31 +08:00
|
|
|
error(Section.getName(Name));
|
2014-10-08 23:28:58 +08:00
|
|
|
uint64_t BaseAddr = Section.getAddress();
|
2014-11-11 17:58:25 +08:00
|
|
|
uint64_t Size = Section.getSize();
|
|
|
|
if (!Size)
|
|
|
|
continue;
|
2011-10-18 01:13:22 +08:00
|
|
|
|
|
|
|
outs() << "Contents of section " << Name << ":\n";
|
2014-11-11 17:58:25 +08:00
|
|
|
if (Section.isBSS()) {
|
2013-04-16 18:53:11 +08:00
|
|
|
outs() << format("<skipping contents of bss section at [%04" PRIx64
|
2014-07-15 00:20:14 +08:00
|
|
|
", %04" PRIx64 ")>\n",
|
|
|
|
BaseAddr, BaseAddr + Size);
|
2013-04-16 18:53:11 +08:00
|
|
|
continue;
|
|
|
|
}
|
2011-10-18 01:13:22 +08:00
|
|
|
|
2015-08-05 15:18:31 +08:00
|
|
|
error(Section.getContents(Contents));
|
2014-07-15 00:20:14 +08:00
|
|
|
|
2011-10-18 01:13:22 +08:00
|
|
|
// Dump out the content as hex and printable ascii characters.
|
|
|
|
for (std::size_t addr = 0, end = Contents.size(); addr < end; addr += 16) {
|
2012-03-10 10:04:38 +08:00
|
|
|
outs() << format(" %04" PRIx64 " ", BaseAddr + addr);
|
2011-10-18 01:13:22 +08:00
|
|
|
// 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) {
|
2013-02-13 05:21:59 +08:00
|
|
|
if (std::isprint(static_cast<unsigned char>(Contents[addr + i]) & 0xFF))
|
2011-10-18 01:13:22 +08:00
|
|
|
outs() << Contents[addr + i];
|
|
|
|
else
|
|
|
|
outs() << ".";
|
|
|
|
}
|
|
|
|
outs() << "\n";
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-06-01 04:35:34 +08:00
|
|
|
void llvm::PrintSymbolTable(const ObjectFile *o, StringRef ArchiveName,
|
|
|
|
StringRef ArchitectureName) {
|
2011-10-19 03:32:17 +08:00
|
|
|
outs() << "SYMBOL TABLE:\n";
|
|
|
|
|
2014-03-19 02:58:51 +08:00
|
|
|
if (const COFFObjectFile *coff = dyn_cast<const COFFObjectFile>(o)) {
|
2015-12-20 17:54:34 +08:00
|
|
|
printCOFFSymbolTable(coff);
|
2014-03-19 02:58:51 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
for (const SymbolRef &Symbol : o->symbols()) {
|
2016-06-25 02:24:42 +08:00
|
|
|
Expected<uint64_t> AddressOrError = Symbol.getAddress();
|
|
|
|
if (!AddressOrError)
|
|
|
|
report_error(ArchiveName, o->getFileName(), AddressOrError.takeError());
|
2015-07-04 02:19:00 +08:00
|
|
|
uint64_t Address = *AddressOrError;
|
2016-09-13 01:08:22 +08:00
|
|
|
if ((Address < StartAddress) || (Address > StopAddress))
|
|
|
|
continue;
|
2016-05-03 04:28:12 +08:00
|
|
|
Expected<SymbolRef::Type> TypeOrError = Symbol.getType();
|
|
|
|
if (!TypeOrError)
|
2016-05-18 01:10:12 +08:00
|
|
|
report_error(ArchiveName, o->getFileName(), TypeOrError.takeError());
|
2016-03-24 04:27:00 +08:00
|
|
|
SymbolRef::Type Type = *TypeOrError;
|
2014-03-19 02:58:51 +08:00
|
|
|
uint32_t Flags = Symbol.getFlags();
|
2016-05-03 04:28:12 +08:00
|
|
|
Expected<section_iterator> SectionOrErr = Symbol.getSection();
|
|
|
|
error(errorToErrorCode(SectionOrErr.takeError()));
|
2015-08-08 07:27:14 +08:00
|
|
|
section_iterator Section = *SectionOrErr;
|
2015-06-03 13:14:22 +08:00
|
|
|
StringRef Name;
|
|
|
|
if (Type == SymbolRef::ST_Debug && Section != o->section_end()) {
|
|
|
|
Section->getName(Name);
|
2015-07-03 04:55:21 +08:00
|
|
|
} else {
|
2016-04-21 05:24:34 +08:00
|
|
|
Expected<StringRef> NameOrErr = Symbol.getName();
|
|
|
|
if (!NameOrErr)
|
2016-06-01 04:35:34 +08:00
|
|
|
report_error(ArchiveName, o->getFileName(), NameOrErr.takeError(),
|
|
|
|
ArchitectureName);
|
2015-07-03 04:55:21 +08:00
|
|
|
Name = *NameOrErr;
|
2015-06-03 13:14:22 +08:00
|
|
|
}
|
2011-10-19 03:32:17 +08:00
|
|
|
|
2014-03-19 02:58:51 +08:00
|
|
|
bool Global = Flags & SymbolRef::SF_Global;
|
|
|
|
bool Weak = Flags & SymbolRef::SF_Weak;
|
|
|
|
bool Absolute = Flags & SymbolRef::SF_Absolute;
|
2015-01-24 04:06:24 +08:00
|
|
|
bool Common = Flags & SymbolRef::SF_Common;
|
2015-05-01 07:08:53 +08:00
|
|
|
bool Hidden = Flags & SymbolRef::SF_Hidden;
|
2015-01-24 04:06:24 +08:00
|
|
|
|
2014-03-19 02:58:51 +08:00
|
|
|
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*";
|
2015-01-24 04:06:24 +08:00
|
|
|
} else if (Common) {
|
|
|
|
outs() << "*COM*";
|
2014-03-19 02:58:51 +08:00
|
|
|
} 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 << ",";
|
2011-10-19 03:32:17 +08:00
|
|
|
}
|
2014-03-19 02:58:51 +08:00
|
|
|
StringRef SectionName;
|
2015-08-05 15:18:31 +08:00
|
|
|
error(Section->getName(SectionName));
|
2014-03-19 02:58:51 +08:00
|
|
|
outs() << SectionName;
|
2011-10-19 03:32:17 +08:00
|
|
|
}
|
2015-06-23 23:45:38 +08:00
|
|
|
|
|
|
|
outs() << '\t';
|
2015-06-24 02:34:25 +08:00
|
|
|
if (Common || isa<ELFObjectFileBase>(o)) {
|
2015-06-26 06:10:04 +08:00
|
|
|
uint64_t Val =
|
|
|
|
Common ? Symbol.getAlignment() : ELFSymbolRef(Symbol).getSize();
|
2015-06-24 02:34:25 +08:00
|
|
|
outs() << format("\t %08" PRIx64 " ", Val);
|
|
|
|
}
|
2015-06-23 23:45:38 +08:00
|
|
|
|
2015-05-01 07:08:53 +08:00
|
|
|
if (Hidden) {
|
|
|
|
outs() << ".hidden ";
|
|
|
|
}
|
|
|
|
outs() << Name
|
2014-03-19 02:58:51 +08:00
|
|
|
<< '\n';
|
2011-10-19 03:32:17 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2012-12-06 04:12:35 +08:00
|
|
|
static void PrintUnwindInfo(const ObjectFile *o) {
|
|
|
|
outs() << "Unwind info:\n\n";
|
|
|
|
|
|
|
|
if (const COFFObjectFile *coff = dyn_cast<COFFObjectFile>(o)) {
|
|
|
|
printCOFFUnwindInfo(coff);
|
2014-08-01 21:07:19 +08:00
|
|
|
} else if (const MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o))
|
|
|
|
printMachOUnwindInfo(MachO);
|
|
|
|
else {
|
2012-12-06 04:12:35 +08:00
|
|
|
// TODO: Extract DWARF dump tool to objdump.
|
|
|
|
errs() << "This operation is only currently supported "
|
2014-08-01 21:07:19 +08:00
|
|
|
"for COFF and MachO object files.\n";
|
2012-12-06 04:12:35 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-01-08 05:02:18 +08:00
|
|
|
void llvm::printExportsTrie(const ObjectFile *o) {
|
2014-08-30 08:20:14 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-01-08 05:02:18 +08:00
|
|
|
void llvm::printRebaseTable(const ObjectFile *o) {
|
2014-09-13 05:34:15 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-01-08 05:02:18 +08:00
|
|
|
void llvm::printBindTable(const ObjectFile *o) {
|
2014-09-16 09:41:51 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-01-08 05:02:18 +08:00
|
|
|
void llvm::printLazyBindTable(const ObjectFile *o) {
|
2014-09-16 09:41:51 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-01-08 05:02:18 +08:00
|
|
|
void llvm::printWeakBindTable(const ObjectFile *o) {
|
2014-09-16 09:41:51 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
2014-09-13 05:34:15 +08:00
|
|
|
|
2015-07-08 10:04:15 +08:00
|
|
|
/// 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;
|
2015-07-29 23:45:39 +08:00
|
|
|
for (auto Sec : ToolSectionFilter(*Obj)) {
|
2015-07-08 10:04:15 +08:00
|
|
|
StringRef Name;
|
|
|
|
Sec.getName(Name);
|
|
|
|
if (Name == ClangASTSectionName) {
|
|
|
|
ClangASTSection = Sec;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (!ClangASTSection)
|
|
|
|
return;
|
|
|
|
|
|
|
|
StringRef ClangASTContents;
|
2015-08-05 15:18:31 +08:00
|
|
|
error(ClangASTSection.getValue().getContents(ClangASTContents));
|
2015-07-08 10:04:15 +08:00
|
|
|
outs().write(ClangASTContents.data(), ClangASTContents.size());
|
|
|
|
}
|
|
|
|
|
2015-06-23 02:03:02 +08:00
|
|
|
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;
|
|
|
|
|
2015-07-29 23:45:39 +08:00
|
|
|
for (auto Sec : ToolSectionFilter(*Obj)) {
|
2015-06-23 02:03:02 +08:00
|
|
|
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;
|
2015-08-05 15:18:31 +08:00
|
|
|
error(FaultMapSection.getValue().getContents(FaultMapContents));
|
2015-06-23 02:03:02 +08:00
|
|
|
|
|
|
|
FaultMapParser FMP(FaultMapContents.bytes_begin(),
|
|
|
|
FaultMapContents.bytes_end());
|
|
|
|
|
|
|
|
outs() << FMP;
|
|
|
|
}
|
|
|
|
|
2016-01-13 08:25:36 +08:00
|
|
|
static void printPrivateFileHeaders(const ObjectFile *o) {
|
|
|
|
if (o->isELF())
|
|
|
|
printELFFileHeader(o);
|
|
|
|
else if (o->isCOFF())
|
|
|
|
printCOFFFileHeader(o);
|
|
|
|
else if (o->isMachO()) {
|
|
|
|
printMachOFileHeader(o);
|
|
|
|
printMachOLoadCommands(o);
|
|
|
|
} else
|
|
|
|
report_fatal_error("Invalid/Unsupported object file format");
|
|
|
|
}
|
|
|
|
|
|
|
|
static void printFirstPrivateFileHeader(const ObjectFile *o) {
|
2015-12-20 06:09:40 +08:00
|
|
|
if (o->isELF())
|
2013-09-28 05:04:00 +08:00
|
|
|
printELFFileHeader(o);
|
2015-12-20 06:09:40 +08:00
|
|
|
else if (o->isCOFF())
|
2013-09-28 05:04:00 +08:00
|
|
|
printCOFFFileHeader(o);
|
2015-12-20 06:09:40 +08:00
|
|
|
else if (o->isMachO())
|
2014-08-23 04:35:18 +08:00
|
|
|
printMachOFileHeader(o);
|
2015-12-20 06:09:40 +08:00
|
|
|
else
|
|
|
|
report_fatal_error("Invalid/Unsupported object file format");
|
2013-09-28 05:04:00 +08:00
|
|
|
}
|
|
|
|
|
2016-05-18 01:10:12 +08:00
|
|
|
static void DumpObject(const ObjectFile *o, const Archive *a = nullptr) {
|
|
|
|
StringRef ArchiveName = a != nullptr ? a->getFileName() : "";
|
2015-07-08 10:04:15 +08:00
|
|
|
// Avoid other output when using a raw option.
|
|
|
|
if (!RawClangAST) {
|
|
|
|
outs() << '\n';
|
2016-05-18 01:10:12 +08:00
|
|
|
if (a)
|
|
|
|
outs() << a->getFileName() << "(" << o->getFileName() << ")";
|
|
|
|
else
|
|
|
|
outs() << o->getFileName();
|
|
|
|
outs() << ":\tfile format " << o->getFileFormatName() << "\n\n";
|
2015-07-08 10:04:15 +08:00
|
|
|
}
|
2011-10-18 01:13:22 +08:00
|
|
|
|
2011-10-08 08:18:30 +08:00
|
|
|
if (Disassemble)
|
2011-10-14 06:17:18 +08:00
|
|
|
DisassembleObject(o, Relocations);
|
|
|
|
if (Relocations && !Disassemble)
|
2011-10-08 08:18:30 +08:00
|
|
|
PrintRelocations(o);
|
2011-10-11 05:21:34 +08:00
|
|
|
if (SectionHeaders)
|
|
|
|
PrintSectionHeaders(o);
|
2011-10-18 01:13:22 +08:00
|
|
|
if (SectionContents)
|
|
|
|
PrintSectionContents(o);
|
2011-10-19 03:32:17 +08:00
|
|
|
if (SymbolTable)
|
2016-05-18 01:10:12 +08:00
|
|
|
PrintSymbolTable(o, ArchiveName);
|
2012-12-06 04:12:35 +08:00
|
|
|
if (UnwindInfo)
|
|
|
|
PrintUnwindInfo(o);
|
2013-09-28 05:04:00 +08:00
|
|
|
if (PrivateHeaders)
|
2016-01-13 08:25:36 +08:00
|
|
|
printPrivateFileHeaders(o);
|
|
|
|
if (FirstPrivateHeader)
|
|
|
|
printFirstPrivateFileHeader(o);
|
2014-08-30 08:20:14 +08:00
|
|
|
if (ExportsTrie)
|
|
|
|
printExportsTrie(o);
|
2014-09-13 05:34:15 +08:00
|
|
|
if (Rebase)
|
|
|
|
printRebaseTable(o);
|
2014-09-16 09:41:51 +08:00
|
|
|
if (Bind)
|
|
|
|
printBindTable(o);
|
|
|
|
if (LazyBind)
|
|
|
|
printLazyBindTable(o);
|
|
|
|
if (WeakBind)
|
|
|
|
printWeakBindTable(o);
|
2015-07-08 10:04:15 +08:00
|
|
|
if (RawClangAST)
|
|
|
|
printRawClangAST(o);
|
2015-06-23 02:03:02 +08:00
|
|
|
if (PrintFaultMaps)
|
|
|
|
printFaultMaps(o);
|
2016-01-26 23:09:42 +08:00
|
|
|
if (DwarfDumpType != DIDT_Null) {
|
|
|
|
std::unique_ptr<DIContext> DICtx(new DWARFContextInMemory(*o));
|
|
|
|
// Dump the complete DWARF structure.
|
|
|
|
DICtx->dump(outs(), DwarfDumpType, true /* DumpEH */);
|
|
|
|
}
|
2011-10-08 08:18:30 +08:00
|
|
|
}
|
|
|
|
|
2016-08-19 00:39:19 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2011-10-08 08:18:30 +08:00
|
|
|
/// @brief Dump each object file in \a a;
|
|
|
|
static void DumpArchive(const Archive *a) {
|
2016-07-14 10:24:01 +08:00
|
|
|
Error Err;
|
|
|
|
for (auto &C : a->children(Err)) {
|
2016-05-18 01:10:12 +08:00
|
|
|
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;
|
|
|
|
}
|
2014-06-17 00:08:36 +08:00
|
|
|
if (ObjectFile *o = dyn_cast<ObjectFile>(&*ChildOrErr.get()))
|
2016-05-18 01:10:12 +08:00
|
|
|
DumpObject(o, a);
|
2016-08-19 00:39:19 +08:00
|
|
|
else if (COFFImportFile *I = dyn_cast<COFFImportFile>(&*ChildOrErr.get()))
|
|
|
|
DumpObject(I, a);
|
2011-10-08 08:18:30 +08:00
|
|
|
else
|
2015-06-05 02:34:11 +08:00
|
|
|
report_error(a->getFileName(), object_error::invalid_file_type);
|
2011-10-08 08:18:30 +08:00
|
|
|
}
|
2016-07-14 10:24:01 +08:00
|
|
|
if (Err)
|
|
|
|
report_error(a->getFileName(), std::move(Err));
|
2011-10-08 08:18:30 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/// @brief Open file and figure out how to dump it.
|
|
|
|
static void DumpInput(StringRef file) {
|
|
|
|
|
2015-01-08 05:02:18 +08:00
|
|
|
// 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);
|
2011-10-08 08:18:30 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Attempt to open the binary.
|
2016-04-07 06:14:09 +08:00
|
|
|
Expected<OwningBinary<Binary>> BinaryOrErr = createBinary(file);
|
|
|
|
if (!BinaryOrErr)
|
2016-05-06 01:43:35 +08:00
|
|
|
report_error(file, BinaryOrErr.takeError());
|
2014-08-20 02:44:46 +08:00
|
|
|
Binary &Binary = *BinaryOrErr.get().getBinary();
|
2011-10-08 08:18:30 +08:00
|
|
|
|
2014-08-01 22:31:55 +08:00
|
|
|
if (Archive *a = dyn_cast<Archive>(&Binary))
|
2011-10-08 08:18:30 +08:00
|
|
|
DumpArchive(a);
|
2014-08-01 22:31:55 +08:00
|
|
|
else if (ObjectFile *o = dyn_cast<ObjectFile>(&Binary))
|
2011-10-08 08:18:30 +08:00
|
|
|
DumpObject(o);
|
2012-08-08 01:53:14 +08:00
|
|
|
else
|
2015-06-05 02:34:11 +08:00
|
|
|
report_error(file, object_error::invalid_file_type);
|
2011-10-08 08:18:30 +08:00
|
|
|
}
|
|
|
|
|
2011-01-20 14:39:06 +08:00
|
|
|
int main(int argc, char **argv) {
|
|
|
|
// Print a stack trace if we signal out.
|
2016-06-09 08:53:21 +08:00
|
|
|
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();
|
2011-07-23 05:58:54 +08:00
|
|
|
llvm::InitializeAllTargetMCs();
|
2011-01-20 14:39:06 +08:00
|
|
|
llvm::InitializeAllDisassemblers();
|
|
|
|
|
2012-05-04 07:20:10 +08:00
|
|
|
// 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");
|
|
|
|
|
2016-08-16 03:49:24 +08:00
|
|
|
if (DisassembleAll || PrintSource || PrintLines)
|
2015-07-24 04:58:49 +08:00
|
|
|
Disassemble = true;
|
2011-10-19 03:32:17 +08:00
|
|
|
if (!Disassemble
|
|
|
|
&& !Relocations
|
|
|
|
&& !SectionHeaders
|
|
|
|
&& !SectionContents
|
2012-12-06 04:12:35 +08:00
|
|
|
&& !SymbolTable
|
2013-01-06 11:56:49 +08:00
|
|
|
&& !UnwindInfo
|
2014-08-30 08:20:14 +08:00
|
|
|
&& !PrivateHeaders
|
2016-01-13 08:25:36 +08:00
|
|
|
&& !FirstPrivateHeader
|
2014-09-13 05:34:15 +08:00
|
|
|
&& !ExportsTrie
|
2014-09-16 09:41:51 +08:00
|
|
|
&& !Rebase
|
|
|
|
&& !Bind
|
|
|
|
&& !LazyBind
|
2015-01-10 03:22:37 +08:00
|
|
|
&& !WeakBind
|
2015-07-08 10:04:15 +08:00
|
|
|
&& !RawClangAST
|
2015-01-16 07:19:11 +08:00
|
|
|
&& !(UniversalHeaders && MachOOpt)
|
2015-01-23 02:55:27 +08:00
|
|
|
&& !(ArchiveHeaders && MachOOpt)
|
2015-01-24 02:52:17 +08:00
|
|
|
&& !(IndirectSymbols && MachOOpt)
|
2015-01-28 05:28:24 +08:00
|
|
|
&& !(DataInCode && MachOOpt)
|
2015-01-31 08:37:11 +08:00
|
|
|
&& !(LinkOptHints && MachOOpt)
|
2015-03-12 06:06:32 +08:00
|
|
|
&& !(InfoPlist && MachOOpt)
|
2015-03-17 04:08:09 +08:00
|
|
|
&& !(DylibsUsed && MachOOpt)
|
|
|
|
&& !(DylibId && MachOOpt)
|
2015-04-02 04:57:01 +08:00
|
|
|
&& !(ObjcMetaData && MachOOpt)
|
2015-07-30 03:08:10 +08:00
|
|
|
&& !(FilterSections.size() != 0 && MachOOpt)
|
2016-01-26 23:09:42 +08:00
|
|
|
&& !PrintFaultMaps
|
|
|
|
&& DwarfDumpType == DIDT_Null) {
|
2011-01-20 14:39:06 +08:00
|
|
|
cl::PrintHelpMessage();
|
|
|
|
return 2;
|
|
|
|
}
|
|
|
|
|
2011-10-08 08:18:30 +08:00
|
|
|
std::for_each(InputFilenames.begin(), InputFilenames.end(),
|
|
|
|
DumpInput);
|
2011-01-20 14:39:06 +08:00
|
|
|
|
2015-08-05 15:18:31 +08:00
|
|
|
return EXIT_SUCCESS;
|
2011-01-20 14:39:06 +08:00
|
|
|
}
|