diff options
author | dim <dim@FreeBSD.org> | 2014-03-21 17:53:59 +0000 |
---|---|---|
committer | dim <dim@FreeBSD.org> | 2014-03-21 17:53:59 +0000 |
commit | 9cedb8bb69b89b0f0c529937247a6a80cabdbaec (patch) | |
tree | c978f0e9ec1ab92dc8123783f30b08a7fd1e2a39 /contrib/llvm/tools/llvm-objdump | |
parent | 03fdc2934eb61c44c049a02b02aa974cfdd8a0eb (diff) | |
download | FreeBSD-src-9cedb8bb69b89b0f0c529937247a6a80cabdbaec.zip FreeBSD-src-9cedb8bb69b89b0f0c529937247a6a80cabdbaec.tar.gz |
MFC 261991:
Upgrade our copy of llvm/clang to 3.4 release. This version supports
all of the features in the current working draft of the upcoming C++
standard, provisionally named C++1y.
The code generator's performance is greatly increased, and the loop
auto-vectorizer is now enabled at -Os and -O2 in addition to -O3. The
PowerPC backend has made several major improvements to code generation
quality and compile time, and the X86, SPARC, ARM32, Aarch64 and SystemZ
backends have all seen major feature work.
Release notes for llvm and clang can be found here:
<http://llvm.org/releases/3.4/docs/ReleaseNotes.html>
<http://llvm.org/releases/3.4/tools/clang/docs/ReleaseNotes.html>
MFC 262121 (by emaste):
Update lldb for clang/llvm 3.4 import
This commit largely restores the lldb source to the upstream r196259
snapshot with the addition of threaded inferior support and a few bug
fixes.
Specific upstream lldb revisions restored include:
SVN git
181387 779e6ac
181703 7bef4e2
182099 b31044e
182650 f2dcf35
182683 0d91b80
183862 15c1774
183929 99447a6
184177 0b2934b
184948 4dc3761
184954 007e7bc
186990 eebd175
Sponsored by: DARPA, AFRL
MFC 262186 (by emaste):
Fix mismerge in r262121
A break statement was lost in the merge. The error had no functional
impact, but restore it to reduce the diff against upstream.
MFC 262303:
Pull in r197521 from upstream clang trunk (by rdivacky):
Use the integrated assembler by default on FreeBSD/ppc and ppc64.
Requested by: jhibbits
MFC 262611:
Pull in r196874 from upstream llvm trunk:
Fix a crash that occurs when PWD is invalid.
MCJIT needs to be able to run in hostile environments, even when PWD
is invalid. There's no need to crash MCJIT in this case.
The obvious fix is to simply leave MCContext's CompilationDir empty
when PWD can't be determined. This way, MCJIT clients,
and other clients that link with LLVM don't need a valid working directory.
If we do want to guarantee valid CompilationDir, that should be done
only for clients of getCompilationDir(). This is as simple as checking
for an empty string.
The only current use of getCompilationDir is EmitGenDwarfInfo, which
won't conceivably run with an invalid working dir. However, in the
purely hypothetically and untestable case that this happens, the
AT_comp_dir will be omitted from the compilation_unit DIE.
This should help fix assertions occurring with ports-mgmt/tinderbox,
when it is using jails, and sometimes invalidates clang's current
working directory.
Reported by: decke
MFC 262809:
Pull in r203007 from upstream clang trunk:
Don't produce an alias between destructors with different calling conventions.
Fixes pr19007.
(Please note that is an LLVM PR identifier, not a FreeBSD one.)
This should fix Firefox and/or libxul crashes (due to problems with
regparm/stdcall calling conventions) on i386.
Reported by: multiple users on freebsd-current
PR: bin/187103
MFC 263048:
Repair recognition of "CC" as an alias for the C++ compiler, since it
was silently broken by upstream for a Windows-specific use-case.
Apparently some versions of CMake still rely on this archaic feature...
Reported by: rakuco
MFC 263049:
Garbage collect the old way of adding the libstdc++ include directories
in clang's InitHeaderSearch.cpp. This has been superseded by David
Chisnall's commit in r255321.
Moreover, if libc++ is used, the libstdc++ include directories should
not be in the search path at all. These directories are now only used
if you pass -stdlib=libstdc++.
Diffstat (limited to 'contrib/llvm/tools/llvm-objdump')
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/COFFDump.cpp | 50 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/ELFDump.cpp | 30 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/MCFunction.cpp | 138 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/MCFunction.h | 100 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/MachODump.cpp | 456 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp | 246 | ||||
-rw-r--r-- | contrib/llvm/tools/llvm-objdump/llvm-objdump.h | 22 |
7 files changed, 415 insertions, 627 deletions
diff --git a/contrib/llvm/tools/llvm-objdump/COFFDump.cpp b/contrib/llvm/tools/llvm-objdump/COFFDump.cpp index 2ada683..5f0bcbb 100644 --- a/contrib/llvm/tools/llvm-objdump/COFFDump.cpp +++ b/contrib/llvm/tools/llvm-objdump/COFFDump.cpp @@ -178,7 +178,7 @@ static error_code resolveSymbol(const std::vector<RelocationRef> &Rels, uint64_t Ofs; if (error_code ec = I->getOffset(Ofs)) return ec; if (Ofs == Offset) { - if (error_code ec = I->getSymbol(Sym)) return ec; + Sym = *I->getSymbol(); break; } } @@ -227,9 +227,51 @@ static void printCOFFSymbolAddress(llvm::raw_ostream &Out, Out << format(" + 0x%04x", Disp); } +// Prints import tables. The import table is a table containing the list of +// DLL name and symbol names which will be linked by the loader. +static void printImportTables(const COFFObjectFile *Obj) { + outs() << "The Import Tables:\n"; + error_code ec; + for (import_directory_iterator i = Obj->import_directory_begin(), + e = Obj->import_directory_end(); + i != e; i = i.increment(ec)) { + if (ec) + return; + + const import_directory_table_entry *Dir; + StringRef Name; + if (i->getImportTableEntry(Dir)) return; + if (i->getName(Name)) return; + + outs() << format(" lookup %08x time %08x fwd %08x name %08x addr %08x\n\n", + static_cast<uint32_t>(Dir->ImportLookupTableRVA), + static_cast<uint32_t>(Dir->TimeDateStamp), + static_cast<uint32_t>(Dir->ForwarderChain), + static_cast<uint32_t>(Dir->NameRVA), + static_cast<uint32_t>(Dir->ImportAddressTableRVA)); + outs() << " DLL Name: " << Name << "\n"; + outs() << " Hint/Ord Name\n"; + const import_lookup_table_entry32 *entry; + if (i->getImportLookupEntry(entry)) + return; + for (; entry->data; ++entry) { + if (entry->isOrdinal()) { + outs() << format(" % 6d\n", entry->getOrdinal()); + continue; + } + uint16_t Hint; + StringRef Name; + if (Obj->getHintName(entry->getHintNameRVA(), Hint, Name)) + return; + outs() << format(" % 6d ", Hint) << Name << "\n"; + } + outs() << "\n"; + } +} + void llvm::printCOFFUnwindInfo(const COFFObjectFile *Obj) { const coff_file_header *Header; - if (error(Obj->getHeader(Header))) return; + if (error(Obj->getCOFFHeader(Header))) return; if (Header->Machine != COFF::IMAGE_FILE_MACHINE_AMD64) { errs() << "Unsupported image machine type " @@ -353,3 +395,7 @@ void llvm::printCOFFUnwindInfo(const COFFObjectFile *Obj) { } } } + +void llvm::printCOFFFileHeader(const object::ObjectFile *Obj) { + printImportTables(dyn_cast<const COFFObjectFile>(Obj)); +} diff --git a/contrib/llvm/tools/llvm-objdump/ELFDump.cpp b/contrib/llvm/tools/llvm-objdump/ELFDump.cpp index bd15231..9c091a4 100644 --- a/contrib/llvm/tools/llvm-objdump/ELFDump.cpp +++ b/contrib/llvm/tools/llvm-objdump/ELFDump.cpp @@ -13,7 +13,7 @@ //===----------------------------------------------------------------------===// #include "llvm-objdump.h" -#include "llvm/Object/ELF.h" +#include "llvm/Object/ELFObjectFile.h" #include "llvm/Support/Format.h" #include "llvm/Support/MathExtras.h" #include "llvm/Support/raw_ostream.h" @@ -21,10 +21,8 @@ using namespace llvm; using namespace llvm::object; -template<class ELFT> -void printProgramHeaders( - const ELFObjectFile<ELFT> *o) { - typedef ELFObjectFile<ELFT> ELFO; +template <class ELFT> void printProgramHeaders(const ELFFile<ELFT> *o) { + typedef ELFFile<ELFT> ELFO; outs() << "Program Header:\n"; for (typename ELFO::Elf_Phdr_Iter pi = o->begin_program_headers(), pe = o->end_program_headers(); @@ -63,7 +61,7 @@ void printProgramHeaders( << format(Fmt, (uint64_t)pi->p_vaddr) << "paddr " << format(Fmt, (uint64_t)pi->p_paddr) - << format("align 2**%u\n", CountTrailingZeros_64(pi->p_align)) + << format("align 2**%u\n", countTrailingZeros<uint64_t>(pi->p_align)) << " filesz " << format(Fmt, (uint64_t)pi->p_filesz) << "memsz " @@ -79,22 +77,18 @@ void printProgramHeaders( void llvm::printELFFileHeader(const object::ObjectFile *Obj) { // Little-endian 32-bit - if (const ELFObjectFile<ELFType<support::little, 4, false> > *ELFObj = - dyn_cast<ELFObjectFile<ELFType<support::little, 4, false> > >(Obj)) - printProgramHeaders(ELFObj); + if (const ELF32LEObjectFile *ELFObj = dyn_cast<ELF32LEObjectFile>(Obj)) + printProgramHeaders(ELFObj->getELFFile()); // Big-endian 32-bit - if (const ELFObjectFile<ELFType<support::big, 4, false> > *ELFObj = - dyn_cast<ELFObjectFile<ELFType<support::big, 4, false> > >(Obj)) - printProgramHeaders(ELFObj); + if (const ELF32BEObjectFile *ELFObj = dyn_cast<ELF32BEObjectFile>(Obj)) + printProgramHeaders(ELFObj->getELFFile()); // Little-endian 64-bit - if (const ELFObjectFile<ELFType<support::little, 8, true> > *ELFObj = - dyn_cast<ELFObjectFile<ELFType<support::little, 8, true> > >(Obj)) - printProgramHeaders(ELFObj); + if (const ELF64LEObjectFile *ELFObj = dyn_cast<ELF64LEObjectFile>(Obj)) + printProgramHeaders(ELFObj->getELFFile()); // Big-endian 64-bit - if (const ELFObjectFile<ELFType<support::big, 8, true> > *ELFObj = - dyn_cast<ELFObjectFile<ELFType<support::big, 8, true> > >(Obj)) - printProgramHeaders(ELFObj); + if (const ELF64BEObjectFile *ELFObj = dyn_cast<ELF64BEObjectFile>(Obj)) + printProgramHeaders(ELFObj->getELFFile()); } diff --git a/contrib/llvm/tools/llvm-objdump/MCFunction.cpp b/contrib/llvm/tools/llvm-objdump/MCFunction.cpp deleted file mode 100644 index 5c67f1b..0000000 --- a/contrib/llvm/tools/llvm-objdump/MCFunction.cpp +++ /dev/null @@ -1,138 +0,0 @@ -//===-- MCFunction.cpp ----------------------------------------------------===// -// -// The LLVM Compiler Infrastructure -// -// This file is distributed under the University of Illinois Open Source -// License. See LICENSE.TXT for details. -// -//===----------------------------------------------------------------------===// -// -// This file defines the algorithm to break down a region of machine code -// into basic blocks and try to reconstruct a CFG from it. -// -//===----------------------------------------------------------------------===// - -#include "MCFunction.h" -#include "llvm/ADT/STLExtras.h" -#include "llvm/MC/MCDisassembler.h" -#include "llvm/MC/MCInst.h" -#include "llvm/MC/MCInstPrinter.h" -#include "llvm/MC/MCInstrAnalysis.h" -#include "llvm/MC/MCInstrDesc.h" -#include "llvm/MC/MCInstrInfo.h" -#include "llvm/Support/MemoryObject.h" -#include "llvm/Support/raw_ostream.h" -#include "llvm/Support/system_error.h" -#include <set> -using namespace llvm; - -MCFunction -MCFunction::createFunctionFromMC(StringRef Name, const MCDisassembler *DisAsm, - const MemoryObject &Region, uint64_t Start, - uint64_t End, const MCInstrAnalysis *Ana, - raw_ostream &DebugOut, - SmallVectorImpl<uint64_t> &Calls) { - std::vector<MCDecodedInst> Instructions; - std::set<uint64_t> Splits; - Splits.insert(Start); - uint64_t Size; - - MCFunction f(Name); - - { - DenseSet<uint64_t> VisitedInsts; - SmallVector<uint64_t, 16> WorkList; - WorkList.push_back(Start); - // Disassemble code and gather basic block split points. - while (!WorkList.empty()) { - uint64_t Index = WorkList.pop_back_val(); - if (VisitedInsts.find(Index) != VisitedInsts.end()) - continue; // Already visited this location. - - for (;Index < End; Index += Size) { - VisitedInsts.insert(Index); - - MCInst Inst; - if (DisAsm->getInstruction(Inst, Size, Region, Index, DebugOut, nulls())){ - Instructions.push_back(MCDecodedInst(Index, Size, Inst)); - if (Ana->isBranch(Inst)) { - uint64_t targ = Ana->evaluateBranch(Inst, Index, Size); - if (targ != -1ULL && targ == Index+Size) - continue; // Skip nop jumps. - - // If we could determine the branch target, make a note to start a - // new basic block there and add the target to the worklist. - if (targ != -1ULL) { - Splits.insert(targ); - WorkList.push_back(targ); - WorkList.push_back(Index+Size); - } - Splits.insert(Index+Size); - break; - } else if (Ana->isReturn(Inst)) { - // Return instruction. This basic block ends here. - Splits.insert(Index+Size); - break; - } else if (Ana->isCall(Inst)) { - uint64_t targ = Ana->evaluateBranch(Inst, Index, Size); - // Add the call to the call list if the destination is known. - if (targ != -1ULL && targ != Index+Size) - Calls.push_back(targ); - } - } else { - errs().write_hex(Index) << ": warning: invalid instruction encoding\n"; - if (Size == 0) - Size = 1; // skip illegible bytes - } - } - } - } - - // Make sure the instruction list is sorted. - std::sort(Instructions.begin(), Instructions.end()); - - // Create basic blocks. - unsigned ii = 0, ie = Instructions.size(); - for (std::set<uint64_t>::iterator spi = Splits.begin(), - spe = llvm::prior(Splits.end()); spi != spe; ++spi) { - MCBasicBlock BB; - uint64_t BlockEnd = *llvm::next(spi); - // Add instructions to the BB. - for (; ii != ie; ++ii) { - if (Instructions[ii].Address < *spi || - Instructions[ii].Address >= BlockEnd) - break; - BB.addInst(Instructions[ii]); - } - f.addBlock(*spi, BB); - } - - std::sort(f.Blocks.begin(), f.Blocks.end()); - - // Calculate successors of each block. - for (MCFunction::iterator i = f.begin(), e = f.end(); i != e; ++i) { - MCBasicBlock &BB = const_cast<MCBasicBlock&>(i->second); - if (BB.getInsts().empty()) continue; - const MCDecodedInst &Inst = BB.getInsts().back(); - - if (Ana->isBranch(Inst.Inst)) { - uint64_t targ = Ana->evaluateBranch(Inst.Inst, Inst.Address, Inst.Size); - if (targ == -1ULL) { - // Indirect branch. Bail and add all blocks of the function as a - // successor. - for (MCFunction::iterator i = f.begin(), e = f.end(); i != e; ++i) - BB.addSucc(i->first); - } else if (targ != Inst.Address+Inst.Size) - BB.addSucc(targ); - // Conditional branches can also fall through to the next block. - if (Ana->isConditionalBranch(Inst.Inst) && llvm::next(i) != e) - BB.addSucc(llvm::next(i)->first); - } else { - // No branch. Fall through to the next block. - if (!Ana->isReturn(Inst.Inst) && llvm::next(i) != e) - BB.addSucc(llvm::next(i)->first); - } - } - - return f; -} diff --git a/contrib/llvm/tools/llvm-objdump/MCFunction.h b/contrib/llvm/tools/llvm-objdump/MCFunction.h deleted file mode 100644 index 6d3a548..0000000 --- a/contrib/llvm/tools/llvm-objdump/MCFunction.h +++ /dev/null @@ -1,100 +0,0 @@ -//===-- MCFunction.h ------------------------------------------------------===// -// -// The LLVM Compiler Infrastructure -// -// This file is distributed under the University of Illinois Open Source -// License. See LICENSE.TXT for details. -// -//===----------------------------------------------------------------------===// -// -// This file defines the data structures to hold a CFG reconstructed from -// machine code. -// -//===----------------------------------------------------------------------===// - -#ifndef LLVM_OBJECTDUMP_MCFUNCTION_H -#define LLVM_OBJECTDUMP_MCFUNCTION_H - -#include "llvm/ADT/ArrayRef.h" -#include "llvm/ADT/DenseSet.h" -#include "llvm/MC/MCInst.h" -#include <map> - -namespace llvm { - -class MCDisassembler; -class MCInstrAnalysis; -class MemoryObject; -class raw_ostream; - -/// MCDecodedInst - Small container to hold an MCInst and associated info like -/// address and size. -struct MCDecodedInst { - uint64_t Address; - uint64_t Size; - MCInst Inst; - - MCDecodedInst() {} - MCDecodedInst(uint64_t Address, uint64_t Size, MCInst Inst) - : Address(Address), Size(Size), Inst(Inst) {} - - bool operator<(const MCDecodedInst &RHS) const { - return Address < RHS.Address; - } -}; - -/// MCBasicBlock - Consists of multiple MCDecodedInsts and a list of successing -/// MCBasicBlocks. -class MCBasicBlock { - std::vector<MCDecodedInst> Insts; - typedef DenseSet<uint64_t> SetTy; - SetTy Succs; -public: - ArrayRef<MCDecodedInst> getInsts() const { return Insts; } - - typedef SetTy::const_iterator succ_iterator; - succ_iterator succ_begin() const { return Succs.begin(); } - succ_iterator succ_end() const { return Succs.end(); } - - bool contains(uint64_t Addr) const { return Succs.count(Addr); } - - void addInst(const MCDecodedInst &Inst) { Insts.push_back(Inst); } - void addSucc(uint64_t Addr) { Succs.insert(Addr); } - - bool operator<(const MCBasicBlock &RHS) const { - return Insts.size() < RHS.Insts.size(); - } -}; - -/// MCFunction - Represents a named function in machine code, containing -/// multiple MCBasicBlocks. -class MCFunction { - const StringRef Name; - // Keep BBs sorted by address. - typedef std::vector<std::pair<uint64_t, MCBasicBlock> > MapTy; - MapTy Blocks; -public: - MCFunction(StringRef Name) : Name(Name) {} - - // Create an MCFunction from a region of binary machine code. - static MCFunction - createFunctionFromMC(StringRef Name, const MCDisassembler *DisAsm, - const MemoryObject &Region, uint64_t Start, uint64_t End, - const MCInstrAnalysis *Ana, raw_ostream &DebugOut, - SmallVectorImpl<uint64_t> &Calls); - - typedef MapTy::const_iterator iterator; - iterator begin() const { return Blocks.begin(); } - iterator end() const { return Blocks.end(); } - - StringRef getName() const { return Name; } - - MCBasicBlock &addBlock(uint64_t Address, const MCBasicBlock &BB) { - Blocks.push_back(std::make_pair(Address, BB)); - return Blocks.back().second; - } -}; - -} - -#endif diff --git a/contrib/llvm/tools/llvm-objdump/MachODump.cpp b/contrib/llvm/tools/llvm-objdump/MachODump.cpp index 6797e2d..86923fd 100644 --- a/contrib/llvm/tools/llvm-objdump/MachODump.cpp +++ b/contrib/llvm/tools/llvm-objdump/MachODump.cpp @@ -12,9 +12,9 @@ //===----------------------------------------------------------------------===// #include "llvm-objdump.h" -#include "MCFunction.h" #include "llvm/ADT/OwningPtr.h" #include "llvm/ADT/STLExtras.h" +#include "llvm/ADT/StringExtras.h" #include "llvm/ADT/Triple.h" #include "llvm/DebugInfo/DIContext.h" #include "llvm/MC/MCAsmInfo.h" @@ -44,10 +44,6 @@ using namespace llvm; using namespace object; static cl::opt<bool> - CFG("cfg", cl::desc("Create a CFG for every symbol in the object file and" - " write it to a graphviz file (MachO-only)")); - -static cl::opt<bool> UseDbg("g", cl::desc("Print line information from debug info if available")); static cl::opt<std::string> @@ -91,105 +87,73 @@ struct SymbolSorter { } }; -// Print additional information about an address, if available. -static void DumpAddress(uint64_t Address, ArrayRef<SectionRef> Sections, - const MachOObjectFile *MachOObj, raw_ostream &OS) { - for (unsigned i = 0; i != Sections.size(); ++i) { - uint64_t SectAddr = 0, SectSize = 0; - Sections[i].getAddress(SectAddr); - Sections[i].getSize(SectSize); - uint64_t addr = SectAddr; - if (SectAddr <= Address && - SectAddr + SectSize > Address) { - StringRef bytes, name; - Sections[i].getContents(bytes); - Sections[i].getName(name); - // Print constant strings. - if (!name.compare("__cstring")) - OS << '"' << bytes.substr(addr, bytes.find('\0', addr)) << '"'; - // Print constant CFStrings. - if (!name.compare("__cfstring")) - OS << "@\"" << bytes.substr(addr, bytes.find('\0', addr)) << '"'; - } - } -} +// Types for the storted data in code table that is built before disassembly +// and the predicate function to sort them. +typedef std::pair<uint64_t, DiceRef> DiceTableEntry; +typedef std::vector<DiceTableEntry> DiceTable; +typedef DiceTable::iterator dice_table_iterator; -typedef std::map<uint64_t, MCFunction*> FunctionMapTy; -typedef SmallVector<MCFunction, 16> FunctionListTy; -static void createMCFunctionAndSaveCalls(StringRef Name, - const MCDisassembler *DisAsm, - MemoryObject &Object, uint64_t Start, - uint64_t End, - MCInstrAnalysis *InstrAnalysis, - uint64_t Address, - raw_ostream &DebugOut, - FunctionMapTy &FunctionMap, - FunctionListTy &Functions) { - SmallVector<uint64_t, 16> Calls; - MCFunction f = - MCFunction::createFunctionFromMC(Name, DisAsm, Object, Start, End, - InstrAnalysis, DebugOut, Calls); - Functions.push_back(f); - FunctionMap[Address] = &Functions.back(); - - // Add the gathered callees to the map. - for (unsigned i = 0, e = Calls.size(); i != e; ++i) - FunctionMap.insert(std::make_pair(Calls[i], (MCFunction*)0)); +static bool +compareDiceTableEntries(const DiceTableEntry i, + const DiceTableEntry j) { + return i.first == j.first; } -// Write a graphviz file for the CFG inside an MCFunction. -static void emitDOTFile(const char *FileName, const MCFunction &f, - MCInstPrinter *IP) { - // Start a new dot file. - std::string Error; - raw_fd_ostream Out(FileName, Error); - if (!Error.empty()) { - errs() << "llvm-objdump: warning: " << Error << '\n'; - return; - } - - Out << "digraph " << f.getName() << " {\n"; - Out << "graph [ rankdir = \"LR\" ];\n"; - for (MCFunction::iterator i = f.begin(), e = f.end(); i != e; ++i) { - bool hasPreds = false; - // Only print blocks that have predecessors. - // FIXME: Slow. - for (MCFunction::iterator pi = f.begin(), pe = f.end(); pi != pe; - ++pi) - if (pi->second.contains(i->first)) { - hasPreds = true; - break; - } - - if (!hasPreds && i != f.begin()) - continue; - - Out << '"' << i->first << "\" [ label=\"<a>"; - // Print instructions. - for (unsigned ii = 0, ie = i->second.getInsts().size(); ii != ie; - ++ii) { - // Escape special chars and print the instruction in mnemonic form. - std::string Str; - raw_string_ostream OS(Str); - IP->printInst(&i->second.getInsts()[ii].Inst, OS, ""); - Out << DOT::EscapeString(OS.str()) << '|'; +static void DumpDataInCode(const char *bytes, uint64_t Size, + unsigned short Kind) { + uint64_t Value; + + switch (Kind) { + case MachO::DICE_KIND_DATA: + switch (Size) { + case 4: + Value = bytes[3] << 24 | + bytes[2] << 16 | + bytes[1] << 8 | + bytes[0]; + outs() << "\t.long " << Value; + break; + case 2: + Value = bytes[1] << 8 | + bytes[0]; + outs() << "\t.short " << Value; + break; + case 1: + Value = bytes[0]; + outs() << "\t.byte " << Value; + break; } - Out << "<o>\" shape=\"record\" ];\n"; - - // Add edges. - for (MCBasicBlock::succ_iterator si = i->second.succ_begin(), - se = i->second.succ_end(); si != se; ++si) - Out << i->first << ":o -> " << *si <<":a\n"; + outs() << "\t@ KIND_DATA\n"; + break; + case MachO::DICE_KIND_JUMP_TABLE8: + Value = bytes[0]; + outs() << "\t.byte " << Value << "\t@ KIND_JUMP_TABLE8"; + break; + case MachO::DICE_KIND_JUMP_TABLE16: + Value = bytes[1] << 8 | + bytes[0]; + outs() << "\t.short " << Value << "\t@ KIND_JUMP_TABLE16"; + break; + case MachO::DICE_KIND_JUMP_TABLE32: + Value = bytes[3] << 24 | + bytes[2] << 16 | + bytes[1] << 8 | + bytes[0]; + outs() << "\t.long " << Value << "\t@ KIND_JUMP_TABLE32"; + break; + default: + outs() << "\t@ data in code kind = " << Kind << "\n"; + break; } - Out << "}\n"; } static void -getSectionsAndSymbols(const macho::Header Header, +getSectionsAndSymbols(const MachO::mach_header Header, MachOObjectFile *MachOObj, std::vector<SectionRef> &Sections, std::vector<SymbolRef> &Symbols, - SmallVectorImpl<uint64_t> &FoundFns) { + SmallVectorImpl<uint64_t> &FoundFns, + uint64_t &BaseSegmentAddress) { error_code ec; for (symbol_iterator SI = MachOObj->begin_symbols(), SE = MachOObj->end_symbols(); SI != SE; SI.increment(ec)) @@ -205,17 +169,27 @@ getSectionsAndSymbols(const macho::Header Header, MachOObjectFile::LoadCommandInfo Command = MachOObj->getFirstLoadCommandInfo(); + bool BaseSegmentAddressSet = false; for (unsigned i = 0; ; ++i) { - if (Command.C.Type == macho::LCT_FunctionStarts) { + if (Command.C.cmd == MachO::LC_FUNCTION_STARTS) { // We found a function starts segment, parse the addresses for later // consumption. - macho::LinkeditDataLoadCommand LLC = + MachO::linkedit_data_command LLC = MachOObj->getLinkeditDataLoadCommand(Command); - MachOObj->ReadULEB128s(LLC.DataOffset, FoundFns); + MachOObj->ReadULEB128s(LLC.dataoff, FoundFns); + } + else if (Command.C.cmd == MachO::LC_SEGMENT) { + MachO::segment_command SLC = + MachOObj->getSegmentLoadCommand(Command); + StringRef SegName = SLC.segname; + if(!BaseSegmentAddressSet && SegName != "__PAGEZERO") { + BaseSegmentAddressSet = true; + BaseSegmentAddress = SLC.vmaddr; + } } - if (i == Header.NumLoadCommands - 1) + if (i == Header.ncmds - 1) break; else Command = MachOObj->getNextLoadCommandInfo(Command); @@ -251,11 +225,12 @@ static void DisassembleInputMachO2(StringRef Filename, InstrAnalysis(TheTarget->createMCInstrAnalysis(InstrInfo.get())); // Set up disassembler. - OwningPtr<const MCAsmInfo> AsmInfo(TheTarget->createMCAsmInfo(TripleName)); + OwningPtr<const MCRegisterInfo> MRI(TheTarget->createMCRegInfo(TripleName)); + OwningPtr<const MCAsmInfo> AsmInfo( + TheTarget->createMCAsmInfo(*MRI, TripleName)); OwningPtr<const MCSubtargetInfo> STI(TheTarget->createMCSubtargetInfo(TripleName, "", "")); OwningPtr<const MCDisassembler> DisAsm(TheTarget->createMCDisassembler(*STI)); - OwningPtr<const MCRegisterInfo> MRI(TheTarget->createMCRegInfo(TripleName)); int AsmPrinterVariant = AsmInfo->getAssemblerDialect(); OwningPtr<MCInstPrinter> IP(TheTarget->createMCInstPrinter(AsmPrinterVariant, *AsmInfo, *InstrInfo, @@ -269,19 +244,41 @@ static void DisassembleInputMachO2(StringRef Filename, outs() << '\n' << Filename << ":\n\n"; - macho::Header Header = MachOOF->getHeader(); + MachO::mach_header Header = MachOOF->getHeader(); + // FIXME: FoundFns isn't used anymore. Using symbols/LC_FUNCTION_STARTS to + // determine function locations will eventually go in MCObjectDisassembler. + // FIXME: Using the -cfg command line option, this code used to be able to + // annotate relocations with the referenced symbol's name, and if this was + // inside a __[cf]string section, the data it points to. This is now replaced + // by the upcoming MCSymbolizer, which needs the appropriate setup done above. std::vector<SectionRef> Sections; std::vector<SymbolRef> Symbols; SmallVector<uint64_t, 8> FoundFns; + uint64_t BaseSegmentAddress; - getSectionsAndSymbols(Header, MachOOF, Sections, Symbols, FoundFns); + getSectionsAndSymbols(Header, MachOOF, Sections, Symbols, FoundFns, + BaseSegmentAddress); - // Make a copy of the unsorted symbol list. FIXME: duplication - std::vector<SymbolRef> UnsortedSymbols(Symbols); // Sort the symbols by address, just in case they didn't come in that way. std::sort(Symbols.begin(), Symbols.end(), SymbolSorter()); + // Build a data in code table that is sorted on by the address of each entry. + uint64_t BaseAddress = 0; + if (Header.filetype == MachO::MH_OBJECT) + Sections[0].getAddress(BaseAddress); + else + BaseAddress = BaseSegmentAddress; + DiceTable Dices; + error_code ec; + for (dice_iterator DI = MachOOF->begin_dices(), DE = MachOOF->end_dices(); + DI != DE; DI.increment(ec)){ + uint32_t Offset; + DI->getOffset(Offset); + Dices.push_back(std::make_pair(BaseAddress + Offset, *DI)); + } + array_pod_sort(Dices.begin(), Dices.end()); + #ifndef NDEBUG raw_ostream &DebugOut = DebugFlag ? dbgs() : nulls(); #else @@ -296,7 +293,7 @@ static void DisassembleInputMachO2(StringRef Filename, // get the sections and supply it to the section name parsing machinery. if (!DSYMFile.empty()) { OwningPtr<MemoryBuffer> Buf; - if (error_code ec = MemoryBuffer::getFileOrSTDIN(DSYMFile.c_str(), Buf)) { + if (error_code ec = MemoryBuffer::getFileOrSTDIN(DSYMFile, Buf)) { errs() << "llvm-objdump: " << Filename << ": " << ec.message() << '\n'; return; } @@ -307,31 +304,24 @@ static void DisassembleInputMachO2(StringRef Filename, diContext.reset(DIContext::getDWARFContext(DbgObj)); } - FunctionMapTy FunctionMap; - FunctionListTy Functions; - for (unsigned SectIdx = 0; SectIdx != Sections.size(); SectIdx++) { + + bool SectIsText = false; + Sections[SectIdx].isText(SectIsText); + if (SectIsText == false) + continue; + StringRef SectName; if (Sections[SectIdx].getName(SectName) || SectName != "__text") continue; // Skip non-text sections DataRefImpl DR = Sections[SectIdx].getRawDataRefImpl(); + StringRef SegmentName = MachOOF->getSectionFinalSegmentName(DR); if (SegmentName != "__TEXT") continue; - // Insert the functions from the function starts segment into our map. - uint64_t VMAddr; - Sections[SectIdx].getAddress(VMAddr); - for (unsigned i = 0, e = FoundFns.size(); i != e; ++i) { - StringRef SectBegin; - Sections[SectIdx].getContents(SectBegin); - uint64_t Offset = (uint64_t)SectBegin.data(); - FunctionMap.insert(std::make_pair(VMAddr + FoundFns[i]-Offset, - (MCFunction*)0)); - } - StringRef Bytes; Sections[SectIdx].getContents(Bytes); StringRefMemoryObject memoryObject(Bytes); @@ -347,10 +337,9 @@ static void DisassembleInputMachO2(StringRef Filename, Sections[SectIdx].getAddress(SectionAddress); RelocOffset -= SectionAddress; - SymbolRef RelocSym; - RI->getSymbol(RelocSym); + symbol_iterator RelocSym = RI->getSymbol(); - Relocs.push_back(std::make_pair(RelocOffset, RelocSym)); + Relocs.push_back(std::make_pair(RelocOffset, *RelocSym)); } array_pod_sort(Relocs.begin(), Relocs.end()); @@ -402,52 +391,56 @@ static void DisassembleInputMachO2(StringRef Filename, symbolTableWorked = true; - if (!CFG) { - // Normal disassembly, print addresses, bytes and mnemonic form. - StringRef SymName; - Symbols[SymIdx].getName(SymName); - - outs() << SymName << ":\n"; - DILineInfo lastLine; - for (uint64_t Index = Start; Index < End; Index += Size) { - MCInst Inst; - - if (DisAsm->getInstruction(Inst, Size, memoryObject, Index, - DebugOut, nulls())) { - uint64_t SectAddress = 0; - Sections[SectIdx].getAddress(SectAddress); - outs() << format("%8" PRIx64 ":\t", SectAddress + Index); - - DumpBytes(StringRef(Bytes.data() + Index, Size)); - IP->printInst(&Inst, outs(), ""); - - // Print debug info. - if (diContext) { - DILineInfo dli = - diContext->getLineInfoForAddress(SectAddress + Index); - // Print valid line info if it changed. - if (dli != lastLine && dli.getLine() != 0) - outs() << "\t## " << dli.getFileName() << ':' - << dli.getLine() << ':' << dli.getColumn(); - lastLine = dli; - } - outs() << "\n"; - } else { - errs() << "llvm-objdump: warning: invalid instruction encoding\n"; - if (Size == 0) - Size = 1; // skip illegible bytes + outs() << SymName << ":\n"; + DILineInfo lastLine; + for (uint64_t Index = Start; Index < End; Index += Size) { + MCInst Inst; + + uint64_t SectAddress = 0; + Sections[SectIdx].getAddress(SectAddress); + outs() << format("%8" PRIx64 ":\t", SectAddress + Index); + + // Check the data in code table here to see if this is data not an + // instruction to be disassembled. + DiceTable Dice; + Dice.push_back(std::make_pair(SectAddress + Index, DiceRef())); + dice_table_iterator DTI = std::search(Dices.begin(), Dices.end(), + Dice.begin(), Dice.end(), + compareDiceTableEntries); + if (DTI != Dices.end()){ + uint16_t Length; + DTI->second.getLength(Length); + DumpBytes(StringRef(Bytes.data() + Index, Length)); + uint16_t Kind; + DTI->second.getKind(Kind); + DumpDataInCode(Bytes.data() + Index, Length, Kind); + continue; + } + + if (DisAsm->getInstruction(Inst, Size, memoryObject, Index, + DebugOut, nulls())) { + DumpBytes(StringRef(Bytes.data() + Index, Size)); + IP->printInst(&Inst, outs(), ""); + + // Print debug info. + if (diContext) { + DILineInfo dli = + diContext->getLineInfoForAddress(SectAddress + Index); + // Print valid line info if it changed. + if (dli != lastLine && dli.getLine() != 0) + outs() << "\t## " << dli.getFileName() << ':' + << dli.getLine() << ':' << dli.getColumn(); + lastLine = dli; } + outs() << "\n"; + } else { + errs() << "llvm-objdump: warning: invalid instruction encoding\n"; + if (Size == 0) + Size = 1; // skip illegible bytes } - } else { - // Create CFG and use it for disassembly. - StringRef SymName; - Symbols[SymIdx].getName(SymName); - createMCFunctionAndSaveCalls( - SymName, DisAsm.get(), memoryObject, Start, End, - InstrAnalysis.get(), Start, DebugOut, FunctionMap, Functions); } } - if (!CFG && !symbolTableWorked) { + if (!symbolTableWorked) { // Reading the symbol table didn't work, disassemble the whole section. uint64_t SectAddress; Sections[SectIdx].getAddress(SectAddress); @@ -470,142 +463,5 @@ static void DisassembleInputMachO2(StringRef Filename, } } } - - if (CFG) { - if (!symbolTableWorked) { - // Reading the symbol table didn't work, create a big __TEXT symbol. - uint64_t SectSize = 0, SectAddress = 0; - Sections[SectIdx].getSize(SectSize); - Sections[SectIdx].getAddress(SectAddress); - createMCFunctionAndSaveCalls("__TEXT", DisAsm.get(), memoryObject, - 0, SectSize, - InstrAnalysis.get(), - SectAddress, DebugOut, - FunctionMap, Functions); - } - for (std::map<uint64_t, MCFunction*>::iterator mi = FunctionMap.begin(), - me = FunctionMap.end(); mi != me; ++mi) - if (mi->second == 0) { - // Create functions for the remaining callees we have gathered, - // but we didn't find a name for them. - uint64_t SectSize = 0; - Sections[SectIdx].getSize(SectSize); - - SmallVector<uint64_t, 16> Calls; - MCFunction f = - MCFunction::createFunctionFromMC("unknown", DisAsm.get(), - memoryObject, mi->first, - SectSize, - InstrAnalysis.get(), DebugOut, - Calls); - Functions.push_back(f); - mi->second = &Functions.back(); - for (unsigned i = 0, e = Calls.size(); i != e; ++i) { - std::pair<uint64_t, MCFunction*> p(Calls[i], (MCFunction*)0); - if (FunctionMap.insert(p).second) - mi = FunctionMap.begin(); - } - } - - DenseSet<uint64_t> PrintedBlocks; - for (unsigned ffi = 0, ffe = Functions.size(); ffi != ffe; ++ffi) { - MCFunction &f = Functions[ffi]; - for (MCFunction::iterator fi = f.begin(), fe = f.end(); fi != fe; ++fi){ - if (!PrintedBlocks.insert(fi->first).second) - continue; // We already printed this block. - - // We assume a block has predecessors when it's the first block after - // a symbol. - bool hasPreds = FunctionMap.find(fi->first) != FunctionMap.end(); - - // See if this block has predecessors. - // FIXME: Slow. - for (MCFunction::iterator pi = f.begin(), pe = f.end(); pi != pe; - ++pi) - if (pi->second.contains(fi->first)) { - hasPreds = true; - break; - } - - uint64_t SectSize = 0, SectAddress; - Sections[SectIdx].getSize(SectSize); - Sections[SectIdx].getAddress(SectAddress); - - // No predecessors, this is a data block. Print as .byte directives. - if (!hasPreds) { - uint64_t End = llvm::next(fi) == fe ? SectSize : - llvm::next(fi)->first; - outs() << "# " << End-fi->first << " bytes of data:\n"; - for (unsigned pos = fi->first; pos != End; ++pos) { - outs() << format("%8x:\t", SectAddress + pos); - DumpBytes(StringRef(Bytes.data() + pos, 1)); - outs() << format("\t.byte 0x%02x\n", (uint8_t)Bytes[pos]); - } - continue; - } - - if (fi->second.contains(fi->first)) // Print a header for simple loops - outs() << "# Loop begin:\n"; - - DILineInfo lastLine; - // Walk over the instructions and print them. - for (unsigned ii = 0, ie = fi->second.getInsts().size(); ii != ie; - ++ii) { - const MCDecodedInst &Inst = fi->second.getInsts()[ii]; - - // If there's a symbol at this address, print its name. - if (FunctionMap.find(SectAddress + Inst.Address) != - FunctionMap.end()) - outs() << FunctionMap[SectAddress + Inst.Address]-> getName() - << ":\n"; - - outs() << format("%8" PRIx64 ":\t", SectAddress + Inst.Address); - DumpBytes(StringRef(Bytes.data() + Inst.Address, Inst.Size)); - - if (fi->second.contains(fi->first)) // Indent simple loops. - outs() << '\t'; - - IP->printInst(&Inst.Inst, outs(), ""); - - // Look for relocations inside this instructions, if there is one - // print its target and additional information if available. - for (unsigned j = 0; j != Relocs.size(); ++j) - if (Relocs[j].first >= SectAddress + Inst.Address && - Relocs[j].first < SectAddress + Inst.Address + Inst.Size) { - StringRef SymName; - uint64_t Addr; - Relocs[j].second.getAddress(Addr); - Relocs[j].second.getName(SymName); - - outs() << "\t# " << SymName << ' '; - DumpAddress(Addr, Sections, MachOOF, outs()); - } - - // If this instructions contains an address, see if we can evaluate - // it and print additional information. - uint64_t targ = InstrAnalysis->evaluateBranch(Inst.Inst, - Inst.Address, - Inst.Size); - if (targ != -1ULL) - DumpAddress(targ, Sections, MachOOF, outs()); - - // Print debug info. - if (diContext) { - DILineInfo dli = - diContext->getLineInfoForAddress(SectAddress + Inst.Address); - // Print valid line info if it changed. - if (dli != lastLine && dli.getLine() != 0) - outs() << "\t## " << dli.getFileName() << ':' - << dli.getLine() << ':' << dli.getColumn(); - lastLine = dli; - } - - outs() << '\n'; - } - } - - emitDOTFile((f.getName().str() + ".dot").c_str(), f, IP.get()); - } - } } } diff --git a/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp b/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp index 247b90f..9bc092e 100644 --- a/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp +++ b/contrib/llvm/tools/llvm-objdump/llvm-objdump.cpp @@ -17,17 +17,26 @@ //===----------------------------------------------------------------------===// #include "llvm-objdump.h" -#include "MCFunction.h" #include "llvm/ADT/OwningPtr.h" #include "llvm/ADT/STLExtras.h" #include "llvm/ADT/StringExtras.h" #include "llvm/ADT/Triple.h" #include "llvm/MC/MCAsmInfo.h" +#include "llvm/MC/MCAtom.h" +#include "llvm/MC/MCContext.h" #include "llvm/MC/MCDisassembler.h" +#include "llvm/MC/MCFunction.h" #include "llvm/MC/MCInst.h" #include "llvm/MC/MCInstPrinter.h" +#include "llvm/MC/MCInstrAnalysis.h" #include "llvm/MC/MCInstrInfo.h" +#include "llvm/MC/MCModule.h" +#include "llvm/MC/MCModuleYAML.h" +#include "llvm/MC/MCObjectDisassembler.h" +#include "llvm/MC/MCObjectFileInfo.h" +#include "llvm/MC/MCObjectSymbolizer.h" #include "llvm/MC/MCRegisterInfo.h" +#include "llvm/MC/MCRelocationInfo.h" #include "llvm/MC/MCSubtargetInfo.h" #include "llvm/Object/Archive.h" #include "llvm/Object/COFF.h" @@ -53,6 +62,7 @@ #include <algorithm> #include <cctype> #include <cstring> + using namespace llvm; using namespace object; @@ -123,6 +133,20 @@ static cl::alias PrivateHeadersShort("p", cl::desc("Alias for --private-headers"), cl::aliasopt(PrivateHeaders)); +static cl::opt<bool> +Symbolize("symbolize", cl::desc("When disassembling instructions, " + "try to symbolize operands.")); + +static cl::opt<bool> +CFG("cfg", cl::desc("Create a CFG for every function found in the object" + " and write it to a graphviz file")); + +// FIXME: Does it make sense to have a dedicated tool for yaml cfg output? +static cl::opt<std::string> +YAMLCFG("yaml-cfg", + cl::desc("Create a CFG and write it as a YAML MCModule."), + cl::value_desc("yaml output file")); + static StringRef ToolName; bool llvm::error(error_code ec) { @@ -137,8 +161,13 @@ static const Target *getTarget(const ObjectFile *Obj = NULL) { // Figure out the target triple. llvm::Triple TheTriple("unknown-unknown-unknown"); if (TripleName.empty()) { - if (Obj) + if (Obj) { TheTriple.setArch(Triple::ArchType(Obj->getArch())); + // TheTriple defaults to ELF, and COFF doesn't have an environment: + // the best we can do here is indicate that it is mach-o. + if (Obj->isMachO()) + TheTriple.setEnvironment(Triple::MachO); + } } else TheTriple.setTriple(Triple::normalize(TripleName)); @@ -156,7 +185,52 @@ static const Target *getTarget(const ObjectFile *Obj = NULL) { return TheTarget; } -void llvm::StringRefMemoryObject::anchor() { } +// Write a graphviz file for the CFG inside an MCFunction. +// FIXME: Use GraphWriter +static void emitDOTFile(const char *FileName, const MCFunction &f, + MCInstPrinter *IP) { + // Start a new dot file. + std::string Error; + raw_fd_ostream Out(FileName, Error); + if (!Error.empty()) { + errs() << "llvm-objdump: warning: " << Error << '\n'; + return; + } + + Out << "digraph \"" << f.getName() << "\" {\n"; + Out << "graph [ rankdir = \"LR\" ];\n"; + for (MCFunction::const_iterator i = f.begin(), e = f.end(); i != e; ++i) { + // Only print blocks that have predecessors. + bool hasPreds = (*i)->pred_begin() != (*i)->pred_end(); + + if (!hasPreds && i != f.begin()) + continue; + + Out << '"' << (*i)->getInsts()->getBeginAddr() << "\" [ label=\"<a>"; + // Print instructions. + for (unsigned ii = 0, ie = (*i)->getInsts()->size(); ii != ie; + ++ii) { + if (ii != 0) // Not the first line, start a new row. + Out << '|'; + if (ii + 1 == ie) // Last line, add an end id. + Out << "<o>"; + + // Escape special chars and print the instruction in mnemonic form. + std::string Str; + raw_string_ostream OS(Str); + IP->printInst(&(*i)->getInsts()->at(ii).Inst, OS, ""); + Out << DOT::EscapeString(OS.str()); + } + Out << "\" shape=\"record\" ];\n"; + + // Add edges. + for (MCBasicBlock::succ_const_iterator si = (*i)->succ_begin(), + se = (*i)->succ_end(); si != se; ++si) + Out << (*i)->getInsts()->getBeginAddr() << ":o -> " + << (*si)->getInsts()->getBeginAddr() << ":a\n"; + } + Out << "}\n"; +} void llvm::DumpBytes(StringRef bytes) { static const char hex_rep[] = "0123456789abcdef"; @@ -207,6 +281,107 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { FeaturesStr = Features.getString(); } + OwningPtr<const MCRegisterInfo> MRI(TheTarget->createMCRegInfo(TripleName)); + if (!MRI) { + errs() << "error: no register info for target " << TripleName << "\n"; + return; + } + + // Set up disassembler. + OwningPtr<const MCAsmInfo> AsmInfo( + TheTarget->createMCAsmInfo(*MRI, TripleName)); + if (!AsmInfo) { + errs() << "error: no assembly info for target " << TripleName << "\n"; + return; + } + + OwningPtr<const MCSubtargetInfo> STI( + TheTarget->createMCSubtargetInfo(TripleName, "", FeaturesStr)); + if (!STI) { + errs() << "error: no subtarget info for target " << TripleName << "\n"; + return; + } + + OwningPtr<const MCInstrInfo> MII(TheTarget->createMCInstrInfo()); + if (!MII) { + errs() << "error: no instruction info for target " << TripleName << "\n"; + return; + } + + OwningPtr<MCDisassembler> DisAsm(TheTarget->createMCDisassembler(*STI)); + if (!DisAsm) { + errs() << "error: no disassembler for target " << TripleName << "\n"; + return; + } + + OwningPtr<const MCObjectFileInfo> MOFI; + OwningPtr<MCContext> Ctx; + + if (Symbolize) { + MOFI.reset(new MCObjectFileInfo); + Ctx.reset(new MCContext(AsmInfo.get(), MRI.get(), MOFI.get())); + OwningPtr<MCRelocationInfo> RelInfo( + TheTarget->createMCRelocationInfo(TripleName, *Ctx.get())); + if (RelInfo) { + OwningPtr<MCSymbolizer> Symzer( + MCObjectSymbolizer::createObjectSymbolizer(*Ctx.get(), RelInfo, Obj)); + if (Symzer) + DisAsm->setSymbolizer(Symzer); + } + } + + OwningPtr<const MCInstrAnalysis> + MIA(TheTarget->createMCInstrAnalysis(MII.get())); + + int AsmPrinterVariant = AsmInfo->getAssemblerDialect(); + OwningPtr<MCInstPrinter> IP(TheTarget->createMCInstPrinter( + AsmPrinterVariant, *AsmInfo, *MII, *MRI, *STI)); + if (!IP) { + errs() << "error: no instruction printer for target " << TripleName + << '\n'; + return; + } + + if (CFG || !YAMLCFG.empty()) { + OwningPtr<MCObjectDisassembler> OD( + new MCObjectDisassembler(*Obj, *DisAsm, *MIA)); + OwningPtr<MCModule> Mod(OD->buildModule(/* withCFG */ true)); + for (MCModule::const_atom_iterator AI = Mod->atom_begin(), + AE = Mod->atom_end(); + AI != AE; ++AI) { + outs() << "Atom " << (*AI)->getName() << ": \n"; + if (const MCTextAtom *TA = dyn_cast<MCTextAtom>(*AI)) { + for (MCTextAtom::const_iterator II = TA->begin(), IE = TA->end(); + II != IE; + ++II) { + IP->printInst(&II->Inst, outs(), ""); + outs() << "\n"; + } + } + } + if (CFG) { + for (MCModule::const_func_iterator FI = Mod->func_begin(), + FE = Mod->func_end(); + FI != FE; ++FI) { + static int filenum = 0; + emitDOTFile((Twine((*FI)->getName()) + "_" + + utostr(filenum) + ".dot").str().c_str(), + **FI, IP.get()); + ++filenum; + } + } + if (!YAMLCFG.empty()) { + std::string Error; + raw_fd_ostream YAMLOut(YAMLCFG.c_str(), Error); + if (!Error.empty()) { + errs() << ToolName << ": warning: " << Error << '\n'; + return; + } + mcmodule2yaml(YAMLOut, *Mod, *MII, *MRI); + } + } + + error_code ec; for (section_iterator i = Obj->begin_sections(), e = Obj->end_sections(); @@ -272,53 +447,13 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { if (Symbols.empty()) Symbols.push_back(std::make_pair(0, name)); - // Set up disassembler. - OwningPtr<const MCAsmInfo> AsmInfo(TheTarget->createMCAsmInfo(TripleName)); - - if (!AsmInfo) { - errs() << "error: no assembly info for target " << TripleName << "\n"; - return; - } - - OwningPtr<const MCSubtargetInfo> STI( - TheTarget->createMCSubtargetInfo(TripleName, "", FeaturesStr)); - if (!STI) { - errs() << "error: no subtarget info for target " << TripleName << "\n"; - return; - } - - OwningPtr<const MCDisassembler> DisAsm( - TheTarget->createMCDisassembler(*STI)); - if (!DisAsm) { - errs() << "error: no disassembler for target " << TripleName << "\n"; - return; - } - - OwningPtr<const MCRegisterInfo> MRI(TheTarget->createMCRegInfo(TripleName)); - if (!MRI) { - errs() << "error: no register info for target " << TripleName << "\n"; - return; - } - - OwningPtr<const MCInstrInfo> MII(TheTarget->createMCInstrInfo()); - if (!MII) { - errs() << "error: no instruction info for target " << TripleName << "\n"; - return; - } - - int AsmPrinterVariant = AsmInfo->getAssemblerDialect(); - OwningPtr<MCInstPrinter> IP(TheTarget->createMCInstPrinter( - AsmPrinterVariant, *AsmInfo, *MII, *MRI, *STI)); - if (!IP) { - errs() << "error: no instruction printer for target " << TripleName - << '\n'; - return; - } + SmallString<40> Comments; + raw_svector_ostream CommentStream(Comments); StringRef Bytes; if (error(i->getContents(Bytes))) break; - StringRefMemoryObject memoryObject(Bytes); + StringRefMemoryObject memoryObject(Bytes, SectionAddr); uint64_t Size; uint64_t Index; uint64_t SectSize; @@ -352,14 +487,17 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { for (Index = Start; Index < End; Index += Size) { MCInst Inst; - if (DisAsm->getInstruction(Inst, Size, memoryObject, Index, - DebugOut, nulls())) { + if (DisAsm->getInstruction(Inst, Size, memoryObject, + SectionAddr + Index, + DebugOut, CommentStream)) { outs() << format("%8" PRIx64 ":", SectionAddr + Index); if (!NoShowRawInsn) { outs() << "\t"; DumpBytes(StringRef(Bytes.data() + Index, Size)); } IP->printInst(&Inst, outs(), ""); + outs() << CommentStream.str(); + Comments.clear(); outs() << "\n"; } else { errs() << ToolName << ": warning: invalid instruction encoding\n"; @@ -632,6 +770,14 @@ static void PrintUnwindInfo(const ObjectFile *o) { } } +static void printPrivateFileHeader(const ObjectFile *o) { + if (o->isELF()) { + printELFFileHeader(o); + } else if (o->isCOFF()) { + printCOFFFileHeader(o); + } +} + static void DumpObject(const ObjectFile *o) { outs() << '\n'; outs() << o->getFileName() @@ -649,8 +795,8 @@ static void DumpObject(const ObjectFile *o) { PrintSymbolTable(o); if (UnwindInfo) PrintUnwindInfo(o); - if (PrivateHeaders && o->isELF()) - printELFFileHeader(o); + if (PrivateHeaders) + printPrivateFileHeader(o); } /// @brief Dump each object file in \a a; diff --git a/contrib/llvm/tools/llvm-objdump/llvm-objdump.h b/contrib/llvm/tools/llvm-objdump/llvm-objdump.h index ca7bced..b716a26 100644 --- a/contrib/llvm/tools/llvm-objdump/llvm-objdump.h +++ b/contrib/llvm/tools/llvm-objdump/llvm-objdump.h @@ -13,7 +13,7 @@ #include "llvm/ADT/StringRef.h" #include "llvm/Support/CommandLine.h" #include "llvm/Support/DataTypes.h" -#include "llvm/Support/MemoryObject.h" +#include "llvm/Support/StringRefMemoryObject.h" namespace llvm { @@ -34,24 +34,8 @@ void DumpBytes(StringRef bytes); void DisassembleInputMachO(StringRef Filename); void printCOFFUnwindInfo(const object::COFFObjectFile* o); void printELFFileHeader(const object::ObjectFile *o); +void printCOFFFileHeader(const object::ObjectFile *o); -class StringRefMemoryObject : public MemoryObject { - virtual void anchor(); - StringRef Bytes; -public: - StringRefMemoryObject(StringRef bytes) : Bytes(bytes) {} - - uint64_t getBase() const { return 0; } - uint64_t getExtent() const { return Bytes.size(); } - - int readByte(uint64_t Addr, uint8_t *Byte) const { - if (Addr >= getExtent()) - return -1; - *Byte = Bytes[Addr]; - return 0; - } -}; - -} +} // end namespace llvm #endif |