diff options
author | Ahmed Bougacha <ahmed.bougacha@gmail.com> | 2013-05-24 01:07:04 +0000 |
---|---|---|
committer | Ahmed Bougacha <ahmed.bougacha@gmail.com> | 2013-05-24 01:07:04 +0000 |
commit | ef99356dfebb96f6f90efb912c2877214bad060e (patch) | |
tree | 76250a4be7eff5e9bec963f6ff0daef8cb8d84bf /tools/llvm-objdump/llvm-objdump.cpp | |
parent | 2c94d0faa0e1c268893d5e04dc77e8a35889db00 (diff) | |
download | llvm-ef99356dfebb96f6f90efb912c2877214bad060e.tar.gz llvm-ef99356dfebb96f6f90efb912c2877214bad060e.tar.bz2 llvm-ef99356dfebb96f6f90efb912c2877214bad060e.tar.xz |
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annotation will be superseded by more related functionality.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182628 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'tools/llvm-objdump/llvm-objdump.cpp')
-rw-r--r-- | tools/llvm-objdump/llvm-objdump.cpp | 89 |
1 files changed, 86 insertions, 3 deletions
diff --git a/tools/llvm-objdump/llvm-objdump.cpp b/tools/llvm-objdump/llvm-objdump.cpp index 570ec7ed6f..d8611d8b3d 100644 --- a/tools/llvm-objdump/llvm-objdump.cpp +++ b/tools/llvm-objdump/llvm-objdump.cpp @@ -17,22 +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/MCObjectDisassembler.h" #include "llvm/MC/MCObjectFileInfo.h" #include "llvm/MC/MCObjectSymbolizer.h" #include "llvm/MC/MCRegisterInfo.h" -#include "llvm/MC/MCSubtargetInfo.h" #include "llvm/MC/MCRelocationInfo.h" +#include "llvm/MC/MCSubtargetInfo.h" #include "llvm/Object/Archive.h" #include "llvm/Object/COFF.h" #include "llvm/Object/MachO.h" @@ -131,6 +135,10 @@ 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")); + static StringRef ToolName; bool llvm::error(error_code ec) { @@ -169,7 +177,51 @@ static const Target *getTarget(const ObjectFile *Obj = NULL) { return TheTarget; } -void llvm::StringRefMemoryObject::anchor() { } +// 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::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"; @@ -269,6 +321,9 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { } } + OwningPtr<const MCInstrAnalysis> + MIA(TheTarget->createMCInstrAnalysis(MII.get())); + int AsmPrinterVariant = AsmInfo->getAssemblerDialect(); OwningPtr<MCInstPrinter> IP(TheTarget->createMCInstPrinter( AsmPrinterVariant, *AsmInfo, *MII, *MRI, *STI)); @@ -278,6 +333,34 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) { return; } + if (CFG) { + 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"; + } + } + } + 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()); + } + } + + error_code ec; for (section_iterator i = Obj->begin_sections(), e = Obj->end_sections(); |