ROSE 2.20.0
Loading...
Searching...
No Matches
Partitioner.h
1#ifndef ROSE_BinaryAnalysis_Partitioner2_Partitioner_H
2#define ROSE_BinaryAnalysis_Partitioner2_Partitioner_H
3#include <featureTests.h>
4#ifdef ROSE_ENABLE_BINARY_ANALYSIS
5#include <Rose/BinaryAnalysis/Partitioner2/BasicTypes.h>
6
7#include <Rose/BinaryAnalysis/Partitioner2/AddressUsageMap.h>
8#include <Rose/BinaryAnalysis/Partitioner2/Configuration.h>
9#include <Rose/BinaryAnalysis/Partitioner2/ControlFlowGraph.h>
10#include <Rose/BinaryAnalysis/Partitioner2/IndirectControlFlow.h>
11#include <Rose/BinaryAnalysis/Partitioner2/Semantics.h>
12
13#include <Rose/BinaryAnalysis/Architecture/BasicTypes.h>
14#include <Rose/BinaryAnalysis/InstructionProvider.h>
15#include <Rose/BinaryAnalysis/InstructionSemantics/SymbolicSemantics.h>
16#include <Rose/BinaryAnalysis/SerialIo.h>
17#include <Rose/BinaryAnalysis/SourceLocations.h>
18#include <Rose/BinaryAnalysis/Unparser/Settings.h>
19#include <Rose/Progress.h>
20
21#include <Sawyer/Attribute.h>
22#include <Sawyer/Callbacks.h>
23#include <Sawyer/IntervalSet.h>
24#include <Sawyer/Map.h>
25#include <Sawyer/Message.h>
26#include <Sawyer/Optional.h>
27#include <Sawyer/ProgressBar.h>
28#include <Sawyer/SharedObject.h>
29#include <Sawyer/SharedPointer.h>
30
31#include <boost/filesystem.hpp>
32#include <boost/format.hpp>
33#include <boost/move/utility_core.hpp>
34#ifdef ROSE_ENABLE_BOOST_SERIALIZATION
35#include <boost/serialization/access.hpp>
36#endif
37
38#ifdef ROSE_ENABLE_FLATBUFFERS
39#include <Rose/BinaryAnalysis/Serialization/FlatBuffers.h>
40#endif
41
42#include <ostream>
43#include <set>
44#include <string>
45#include <vector>
46
47namespace Rose {
48namespace BinaryAnalysis {
49namespace Partitioner2 {
50
263class ROSE_DLL_API Partitioner /*final*/
264 : public Sawyer::SharedObject, public Sawyer::SharedFromThis<Partitioner>, public Sawyer::Attribute::Storage<> {
265 BOOST_MOVABLE_BUT_NOT_COPYABLE(Partitioner)
266
267
269 //
270 // Types
271 //
274public:
282 // Callback list types
285 typedef std::vector<FunctionPrologueMatcherPtr> FunctionPrologueMatchers;
286 typedef std::vector<FunctionPaddingMatcherPtr> FunctionPaddingMatchers;
289 struct Thunk {
292 Thunk(const BasicBlockPtr&, Address target);
293 ~Thunk();
294 };
295
298
301 //
302 // Data members
303 //
306private:
307 friend class Rose::BinaryAnalysis::Serialization::FlatBuffers::Deserializer;
308
309 BasePartitionerSettings settings_; // settings adjustable from the command-line
310 Configuration config_; // configuration information about functions, blocks, etc.
311 Architecture::BaseConstPtr architecture_; // architecture information such as the ISA, word size, etc.
312 InstructionProvider::Ptr instructionProvider_; // cache for all disassembled instructions
313 MemoryMap::Ptr memoryMap_; // description of memory, especially insns and non-writable
314 SgAsmInterpretation *interpretation_ = nullptr; // Interpretation corresponding to the memory map
315 PartitionerPtr secondaryPartitioner_; // optional runtime-only secondary partitioner
316 ControlFlowGraph cfg_; // basic blocks that will become part of the ROSE AST
317 CfgVertexIndex vertexIndex_; // Vertex-by-address index for the CFG
318 AddressUsageMap aum_; // How addresses are used for each address represented by the CFG
319 SmtSolverPtr solver_; // Satisfiable modulo theory solver used by semantic expressions
320 Functions functions_; // List of all attached functions by entry address
321 bool autoAddCallReturnEdges_ = false; // Add E_CALL_RETURN edges when blocks are attached to CFG?
322 bool assumeFunctionsReturn_ = true; // Assume that unproven functions return to caller?
323 size_t stackDeltaInterproceduralLimit_ = 1; // Max depth of call stack when computing stack deltas
324 AddressNameMap addressNames_; // Names for various addresses
325 SourceLocations sourceLocations_; // Mapping between source locations and addresses
326 SemanticMemoryParadigm semanticMemoryParadigm_ = LIST_BASED_MEMORY; // Slow and precise, or fast and imprecise?
327 Unparser::BasePtr unparser_; // For unparsing things to pseudo-assembly
328 Unparser::BasePtr insnUnparser_; // For unparsing single instructions in diagnostics
329 Unparser::BasePtr insnPlainUnparser_; // For unparsing just instruction mnemonic and operands
330 IndirectControlFlow::State icf_; // State for various indirect control flow recovery analyses
331
332 // Callback lists
333 CfgAdjustmentCallbacks cfgAdjustmentCallbacks_;
334 BasicBlockCallbacks basicBlockCallbacks_;
335 FunctionPrologueMatchers functionPrologueMatchers_;
336 FunctionPaddingMatchers functionPaddingMatchers_;
337
338 // Special CFG vertices.
339 ControlFlowGraph::VertexIterator undiscoveredVertex_;
340 ControlFlowGraph::VertexIterator indeterminateVertex_;
341 ControlFlowGraph::VertexIterator nonexistingVertex_;
342 static const size_t nSpecialVertices = 3;
343
344 // Optional cached information
345 Sawyer::Optional<Address> elfGotVa_; // address of ELF GOT, set by findElfGotVa
346
347 // Protects the following data members
348 mutable SAWYER_THREAD_TRAITS::Mutex mutex_;
349 Progress::Ptr progress_; // Progress reporter to update, or null
350 mutable size_t cfgProgressTotal_ = 0; // Expected total for the CFG progress bar; initialized at first report
351
354 //
355 // Serialization
356 //
359#ifdef ROSE_ENABLE_BOOST_SERIALIZATION
360private:
361 friend class boost::serialization::access;
362 template<class Archive> void serializeCommon(Archive&, unsigned);
363 template<class Archive> void save(Archive&, unsigned) const;
364 template<class Archive> void load(Archive&, unsigned);
365 BOOST_SERIALIZATION_SPLIT_MEMBER();
366#endif
367
368#ifdef ROSE_ENABLE_FLATBUFFERS
369private:
370 friend class Rose::BinaryAnalysis::Serialization::FlatBuffers::Deserializer;
371#endif
372
375 //
376 // Constructors
377 //
380private:
381 Partitioner(); // needed for Boost serialization
382
383 // Partitioner objects are reference counted and always allocated on the heap. Use the `instance` methods to construct
384 // these objects. Also, since the Partitioner class is final, we make the constructors private instead of the usual
385 // protected constructors elsewhere in ROSE.
388public:
389 ~Partitioner();
390
391public:
397
403
408 static PartitionerPtr instanceFromRbaFile(const boost::filesystem::path&, Serialization::Format = Serialization::BINARY);
409
411 void saveAsRbaFile(const boost::filesystem::path &name, Serialization::Format fmt) const;
412
414 Partitioner(BOOST_RV_REF(Partitioner));
415
418
426
428 void clear();
429
445
463
486
487
490 //
491 // Unparsing
492 //
495public:
524
529
538 std::string unparse(SgAsmInstruction*) const;
539 void unparse(std::ostream&, SgAsmInstruction*) const;
540 void unparse(std::ostream&, const BasicBlockPtr&) const;
541 void unparse(std::ostream&, const DataBlockPtr&) const;
542 void unparse(std::ostream&, const FunctionPtr&) const;
543 void unparse(std::ostream&) const;
549 std::string unparsePlain(SgAsmInstruction*) const;
550
553 //
554 // Partitioner CFG queries
555 //
558public:
564 size_t nBytes() const;
565
573 ControlFlowGraph::VertexIterator undiscoveredVertex();
574 ControlFlowGraph::ConstVertexIterator undiscoveredVertex() const;
587 ControlFlowGraph::VertexIterator indeterminateVertex();
588 ControlFlowGraph::ConstVertexIterator indeterminateVertex() const;
600 ControlFlowGraph::VertexIterator nonexistingVertex();
601 ControlFlowGraph::ConstVertexIterator nonexistingVertex() const;
610 const ControlFlowGraph& cfg() const;
611
618 const AddressUsageMap& aum() const;
619
622
627 std::vector<AddressUser> users(Address) const;
628
636 std::set<Address> ghostSuccessors() const;
637
666 bool isEdgeIntraProcedural(ControlFlowGraph::ConstEdgeIterator edge, const FunctionPtr&) const;
667 bool isEdgeIntraProcedural(const ControlFlowGraph::Edge &edge, const FunctionPtr&) const;
668 bool isEdgeIntraProcedural(ControlFlowGraph::ConstEdgeIterator edge) const;
669 bool isEdgeIntraProcedural(const ControlFlowGraph::Edge &edge) const;
706 bool isEdgeInterProcedural(ControlFlowGraph::ConstEdgeIterator edge) const;
707 bool isEdgeInterProcedural(ControlFlowGraph::ConstEdgeIterator edge, const FunctionPtr &sourceFunction) const;
708 bool isEdgeInterProcedural(ControlFlowGraph::ConstEdgeIterator edge, const FunctionPtr &sourceFunction,
709 const FunctionPtr &targetFunction) const;
710
711 bool isEdgeInterProcedural(const ControlFlowGraph::Edge &edge) const;
712 bool isEdgeInterProcedural(const ControlFlowGraph::Edge &edge, const FunctionPtr &sourceFunction) const;
713 bool isEdgeInterProcedural(const ControlFlowGraph::Edge &edge, const FunctionPtr &sourceFunction,
714 const FunctionPtr &targetFunction) const;
721 //
722 // Partitioner instruction operations
723 //
726public:
732 size_t nInstructions() const;
733
753 ControlFlowGraph::ConstVertexIterator instructionVertex(Address insnVa) const;
754
763 std::vector<SgAsmInstruction*> instructionsOverlapping(const AddressInterval&) const;
764
773 std::vector<SgAsmInstruction*> instructionsSpanning(const AddressInterval&) const;
774
784 std::vector<SgAsmInstruction*> instructionsContainedIn(const AddressInterval&) const;
785
794
808
814
815
816
819 //
820 // Partitioner basic block placeholder operations
821 //
824public:
834 size_t nPlaceholders() const;
835
844 bool placeholderExists(Address startVa) const;
845
856 ControlFlowGraph::VertexIterator findPlaceholder(Address startVa);
857 ControlFlowGraph::ConstVertexIterator findPlaceholder(Address startVa) const;
876 ControlFlowGraph::VertexIterator insertPlaceholder(Address startVa);
877
891 BasicBlockPtr erasePlaceholder(const ControlFlowGraph::ConstVertexIterator &placeholder) /*final*/;
899 //
900 // Partitioner basic block operations
901 //
904public:
931
940 size_t nBasicBlocks() const;
941
949 std::vector<BasicBlockPtr> basicBlocks() const;
950
985 std::vector<BasicBlockPtr> basicBlocksOverlapping(const AddressInterval&) const;
986
997 std::vector<BasicBlockPtr> basicBlocksSpanning(const AddressInterval&) const;
998
1008 std::vector<BasicBlockPtr> basicBlocksContainedIn(const AddressInterval&) const;
1009
1017
1028
1035
1062 BasicBlockPtr detachBasicBlock(const ControlFlowGraph::ConstVertexIterator &placeholder);
1076 ControlFlowGraph::VertexIterator truncateBasicBlock(const ControlFlowGraph::ConstVertexIterator &basicBlock,
1077 SgAsmInstruction *insn);
1078
1112 void attachBasicBlock(const ControlFlowGraph::ConstVertexIterator &placeholder, const BasicBlockPtr&);
1201 BasicBlockPtr discoverBasicBlock(const ControlFlowGraph::ConstVertexIterator &placeholder) const;
1219
1228 std::vector<Address> basicBlockConcreteSuccessors(const BasicBlockPtr&, bool *isComplete=NULL) const;
1229
1248 std::set<Address> basicBlockGhostSuccessors(const BasicBlockPtr&) const;
1249
1259 bool basicBlockIsFunctionCall(const BasicBlockPtr&, Precision::Level precision = Precision::HIGH) const;
1260
1272
1278
1320 basicBlockStackDeltaIn(const BasicBlockPtr&, const FunctionPtr &function) const;
1321
1323 basicBlockStackDeltaOut(const BasicBlockPtr&, const FunctionPtr &function) const;
1334 void forgetStackDeltas() const;
1335 void forgetStackDeltas(const FunctionPtr&) const;
1402 Sawyer::Optional<bool> basicBlockOptionalMayReturn(const ControlFlowGraph::ConstVertexIterator&) const;
1412
1413private:
1414 // Per-vertex data used during may-return analysis
1415 struct MayReturnVertexInfo {
1416 enum State {INIT, CALCULATING, FINISHED};
1417 State state; // current state of vertex
1418 bool processedCallees; // have we processed BBs this vertex calls?
1419 boost::logic::tribool anyCalleesReturn; // do any of those called BBs have a true may-return value?
1420 boost::logic::tribool result; // final result (eventually cached in BB)
1421 MayReturnVertexInfo(): state(INIT), processedCallees(false), anyCalleesReturn(false), result(boost::indeterminate) {}
1422 };
1423
1424 // Is edge significant for analysis? See .C file for full documentation.
1425 bool mayReturnIsSignificantEdge(const ControlFlowGraph::ConstEdgeIterator &edge,
1426 std::vector<MayReturnVertexInfo> &vertexInfo) const;
1427
1428 // Determine (and cache in vertexInfo) whether any callees return.
1429 boost::logic::tribool mayReturnDoesCalleeReturn(const ControlFlowGraph::ConstVertexIterator &vertex,
1430 std::vector<MayReturnVertexInfo> &vertexInfo) const;
1431
1432 // Maximum may-return result from significant successors including phantom call-return edge.
1433 boost::logic::tribool mayReturnDoesSuccessorReturn(const ControlFlowGraph::ConstVertexIterator &vertex,
1434 std::vector<MayReturnVertexInfo> &vertexInfo) const;
1435
1436 // The guts of the may-return analysis
1437 Sawyer::Optional<bool> basicBlockOptionalMayReturn(const ControlFlowGraph::ConstVertexIterator &start,
1438 std::vector<MayReturnVertexInfo> &vertexInfo) const;
1439
1440
1441
1444 //
1445 // Partitioner data block operations
1446 //
1449public:
1455 size_t nDataBlocks() const;
1456
1464
1474
1487
1495
1506
1520
1530 std::vector<DataBlockPtr> dataBlocksOverlapping(const AddressInterval&) const;
1531
1541 std::vector<DataBlockPtr> dataBlocksSpanning(const AddressInterval&) const;
1542
1552 std::vector<DataBlockPtr> dataBlocksContainedIn(const AddressInterval&) const;
1553
1561
1567 std::vector<DataBlockPtr> dataBlocks() const;
1568
1569
1570
1573 //
1574 // Partitioner function operations
1575 //
1578public:
1584 size_t nFunctions() const;
1585
1605 FunctionPtr functionExists(const BasicBlockPtr &entryBlock) const;
1614 std::vector<FunctionPtr> functions() const;
1615
1625 std::vector<FunctionPtr> functionsOverlapping(const AddressInterval&) const;
1626
1637 std::vector<FunctionPtr> functionsSpanning(const AddressInterval&) const;
1638
1648 std::vector<FunctionPtr> functionsContainedIn(const AddressInterval&) const;
1649
1667 void functionExtent(const FunctionPtr &function, AddressIntervalSet &retval /*in,out*/) const;
1669 void functionBasicBlockExtent(const FunctionPtr &function, AddressIntervalSet &retval /*in,out*/) const;
1671 void functionDataBlockExtent(const FunctionPtr &function, AddressIntervalSet &retval /*in,out*/) const;
1711
1746
1752 std::vector<Function::Ptr> entryFunctions();
1753
1788 std::vector<FunctionPtr>
1789 functionsOwningBasicBlock(const ControlFlowGraph::Vertex&, bool doSort = true) const;
1790
1791 std::vector<FunctionPtr>
1792 functionsOwningBasicBlock(const ControlFlowGraph::ConstVertexIterator&, bool doSort = true) const;
1793
1794 std::vector<FunctionPtr>
1795 functionsOwningBasicBlock(Address bblockVa, bool doSort = true) const;
1796
1797 std::vector<FunctionPtr>
1798 functionsOwningBasicBlock(const BasicBlockPtr&, bool doSort = true) const;
1799
1800 template<class Container> // container can hold any type accepted by functionsOwningBasicBlock
1801 std::vector<FunctionPtr>
1802 functionsOwningBasicBlocks(const Container &bblocks) const {
1803 std::vector<FunctionPtr> retval;
1804 for (const typename Container::value_type& bblock: bblocks) {
1805 for (const FunctionPtr &function: functionsOwningBasicBlock(bblock, false))
1806 insertUnique(retval, function, sortFunctionsByAddress);
1807 }
1808 return retval;
1809 }
1821 std::vector<FunctionPtr> discoverCalledFunctions() const;
1822
1834 std::vector<FunctionPtr> discoverFunctionEntryVertices() const;
1835
1846
1857 void discoverFunctionBasicBlocks(const FunctionPtr &function) const;
1858
1865 std::set<Address> functionGhostSuccessors(const FunctionPtr&) const;
1866
1875
1896
1901
1909
1914
1950 const CallingConvention::Definition::Ptr &dflt) const;
1969
2031 void fixInterFunctionEdge(const ControlFlowGraph::ConstEdgeIterator&);
2050 bool functionIsNoop(const FunctionPtr&) const;
2051
2057 void allFunctionIsNoop() const;
2058
2074 std::set<Address> functionDataFlowConstants(const FunctionPtr&) const;
2075
2076
2077
2080 //
2081 // Callbacks
2082 //
2085public:
2119public:
2155 std::vector<FunctionPtr> nextFunctionPrologue(Address startVa);
2156 std::vector<FunctionPtr> nextFunctionPrologue(Address startVa, Address &lastSearchedVa /*out*/);
2159public:
2177
2178
2179
2182 //
2183 // Partitioner miscellaneous
2184 //
2187public:
2199 void dumpCfg(std::ostream&, const std::string &prefix="", bool showBlocks=true, bool computeProperties=true) const;
2200
2214 void cfgGraphViz(std::ostream&, const AddressInterval &restrict = AddressInterval::whole(), bool showNeighbors=true) const;
2215
2221 static std::string vertexName(const ControlFlowGraph::Vertex&);
2222 std::string vertexName(const ControlFlowGraph::ConstVertexIterator&) const;
2228 static std::string vertexNameEnd(const ControlFlowGraph::Vertex&);
2229
2235 static std::string edgeNameSrc(const ControlFlowGraph::Edge&);
2236 std::string edgeNameSrc(const ControlFlowGraph::ConstEdgeIterator&) const;
2244 static std::string edgeNameDst(const ControlFlowGraph::Edge&);
2245 std::string edgeNameDst(const ControlFlowGraph::ConstEdgeIterator&) const;
2253 static std::string edgeName(const ControlFlowGraph::Edge&);
2254 std::string edgeName(const ControlFlowGraph::ConstEdgeIterator&) const;
2260 static std::string basicBlockName(const BasicBlockPtr&);
2261
2265 static std::string dataBlockName(const DataBlockPtr&);
2266
2270 static std::string functionName(const FunctionPtr&);
2271
2277
2303 void updateProgress(const std::string &phase, double completion) const;
2304
2306 void showStatistics() const;
2307
2308 // Checks consistency of internal data structures when debugging is enable (when NDEBUG is not defined).
2309 void checkConsistency() const;
2310
2317
2322
2333 //
2334 // Settings
2335 //
2338public:
2339
2359 void enableSymbolicSemantics(bool = true);
2416 void addressName(Address, const std::string&);
2417 const std::string& addressName(Address) const;
2446 //
2447 // Instruction semantics
2448 //
2451public:
2472
2496
2497
2498
2501 //
2502 // Python API support functions
2503 //
2506#ifdef ROSE_ENABLE_PYTHON_API
2507 void pythonUnparse() const;
2508#endif
2509
2510
2511
2514 //
2515 // Partitioner internal utilities
2516 //
2519private:
2520 void init(const MemoryMap::Ptr&);
2521 void init(const Partitioner&);
2522 void updateCfgProgress();
2523
2524private:
2525 // Convert a CFG vertex iterator from one partitioner to another. This is called during copy construction when the source
2526 // and destination CFGs are identical.
2527 ControlFlowGraph::VertexIterator convertFrom(const Partitioner &other,
2528 ControlFlowGraph::ConstVertexIterator otherIter);
2529
2530 // Adjusts edges for a placeholder vertex. This method erases all outgoing edges for the specified placeholder vertex and
2531 // then inserts a single edge from the placeholder to the special "undiscovered" vertex. */
2532 ControlFlowGraph::EdgeIterator adjustPlaceholderEdges(const ControlFlowGraph::VertexIterator &placeholder);
2533
2534 // Adjusts edges for a non-existing basic block. This method erases all outgoing edges for the specified vertex and
2535 // then inserts a single edge from the vertex to the special "non-existing" vertex. */
2536 ControlFlowGraph::EdgeIterator adjustNonexistingEdges(const ControlFlowGraph::VertexIterator &vertex);
2537
2538 // Implementation for the discoverBasicBlock methods. The startVa must not be the address of an existing placeholder.
2539 BasicBlockPtr discoverBasicBlockInternal(Address startVa) const;
2540
2541 // This method is called whenever a new placeholder is inserted into the CFG or a new basic block is attached to the
2542 // CFG/AUM. The call happens immediately after the CFG/AUM are updated.
2543 void bblockAttached(const ControlFlowGraph::VertexIterator &newVertex);
2544
2545 // This method is called whenever a basic block is detached from the CFG/AUM or when a placeholder is erased from the CFG.
2546 // The call happens immediately after the CFG/AUM are updated.
2547 void bblockDetached(Address startVa, const BasicBlockPtr &removedBlock);
2548
2549 // Rebuild the vertexIndex_ and other cache-like data members from the control flow graph
2550 void rebuildVertexIndices();
2551};
2552
2553} // namespace
2554} // namespace
2555} // namespace
2556
2557#endif
2558#endif
Provides and caches instructions.
Partitions instructions into basic blocks and functions.
AddressIntervalSet basicBlockInstructionExtent(const BasicBlockPtr &) const
Returns the addresses used by basic block instructions.
Sawyer::Callbacks< CfgAdjustmentCallback::Ptr > CfgAdjustmentCallbacks
See cfgAdjustmentCallbacks.
const Configuration & configuration() const
Property: Configuration information.
ControlFlowGraph::VertexIterator nonexistingVertex()
Returns the special "non-existing" vertex.
ControlFlowGraph::ConstVertexIterator nonexistingVertex() const
Returns the special "non-existing" vertex.
static std::string dataBlockName(const DataBlockPtr &)
Name of a data block.
bool basicBlockIsFunctionReturn(const BasicBlockPtr &) const
Determine if a basic block looks like a function return.
std::vector< Function::Ptr > entryFunctions()
Entry points of the binary.
std::vector< BasicBlockPtr > basicBlocksContainedIn(const AddressInterval &) const
Returns basic blocks that are fully contained in an address interval.
FunctionPrologueMatchers & functionPrologueMatchers()
Ordered list of function prologue matchers.
void addressName(Address, const std::string &)
Property: Name for address.
ControlFlowGraph::VertexIterator undiscoveredVertex()
Returns the special "undiscovered" vertex.
void basicBlockDropSemantics() const
Immediately drop semantic information for all attached basic blocks.
size_t nDataBlocks() const
Returns the number of data blocks attached to the CFG/AUM.
ControlFlowGraph::ConstVertexIterator indeterminateVertex() const
Returns the special "indeterminate" vertex.
void allFunctionCallingConvention() const
Compute calling conventions for all functions.
InstructionSemantics::BaseSemantics::SValuePtr functionStackDelta(const FunctionPtr &function) const
Stack delta analysis for one function.
void interpretation(SgAsmInterpretation *)
Property: Interpretation corresponding to the memory map.
BasicBlockPtr erasePlaceholder(Address startVa)
Remove a basic block placeholder from the CFG/AUM.
Unparser::BasePtr unparser() const
Returns an unparser.
void forgetFunctionIsNoop() const
Clears cached function no-op analysis results.
CfgAdjustmentCallbacks & cfgAdjustmentCallbacks()
List of all callbacks invoked when the CFG is adjusted.
Sawyer::Optional< bool > functionOptionalMayReturn(const FunctionPtr &function) const
May-return analysis for one function.
std::vector< SgAsmInstruction * > instructionsContainedIn(const AddressInterval &) const
Returns instructions that are fully contained in an address interval.
Sawyer::Optional< bool > basicBlockOptionalMayReturn(const BasicBlockPtr &) const
Determine if part of the CFG can pop the top stack frame.
BasicBlockSuccessors basicBlockSuccessors(const BasicBlockPtr &, Precision::Level precision=Precision::HIGH) const
Determine successors for a basic block.
std::vector< DataBlockPtr > dataBlocksContainedIn(const AddressInterval &) const
Returns data blocks that are fully contained in an address interval.
SemanticMemoryParadigm semanticMemoryParadigm() const
Property: Whether to use map- or list-based memory states.
void allFunctionCallingConvention(const CallingConvention::Definition::Ptr &dflt) const
Compute calling conventions for all functions.
FunctionCallGraph functionCallGraph(AllowParallelEdges::Type allowParallelEdges) const
Returns a function call graph.
size_t stackDeltaInterproceduralLimit() const
Property: max depth for inter-procedural stack delta analysis.
void stackDeltaInterproceduralLimit(size_t)
Property: max depth for inter-procedural stack delta analysis.
ControlFlowGraph::VertexIterator insertPlaceholder(Address startVa)
Insert a basic-block placeholder.
PartitionerConstPtr secondaryPartitioner() const
Property: Optional secondary partitioner.
FunctionPtr functionExists(const FunctionPtr &function) const
Determines whether a function exists in the CFG/AUM.
void forgetStackDeltas(const FunctionPtr &) const
Clears all cached stack deltas.
void unparse(std::ostream &, const DataBlockPtr &) const
Unparse some entity.
std::vector< FunctionPtr > functionsOverlapping(const AddressInterval &) const
Returns functions that overlap with specified address interval.
DataBlockPtr matchFunctionPadding(const FunctionPtr &)
Finds function padding.
void configureInsnPlainUnparser(const Unparser::BasePtr &) const
Configure plain single-instruction unparser.
SgAsmInstruction * discoverInstruction(Address startVa) const
Discover an instruction.
bool functionIsNoop(const FunctionPtr &) const
Function no-op analysis.
void fixInterFunctionEdge(const ControlFlowGraph::ConstEdgeIterator &)
Adjust inter-function edge types.
ControlFlowGraph::VertexIterator truncateBasicBlock(const ControlFlowGraph::ConstVertexIterator &basicBlock, SgAsmInstruction *insn)
Truncate an attached basic-block.
Sawyer::Optional< Thunk > functionIsThunk(const FunctionPtr &) const
True if function is a thunk.
size_t attachFunctionBasicBlocks(const Functions &)
Create placeholders for function basic blocks.
const ControlFlowGraph & cfg() const
Returns the control flow graph.
const CallingConvention::Analysis & functionCallingConvention(const FunctionPtr &, const CallingConvention::Definition::Ptr &dflt) const
Calling convention analysis for one function.
const SourceLocations & sourceLocations() const
Property: Source locations.
Partitioner & operator=(BOOST_RV_REF(Partitioner))
Move assignment.
bool isEdgeInterProcedural(ControlFlowGraph::ConstEdgeIterator edge) const
Determine if an edge is inter-procedural.
void checkingCallBranch(bool)
Property: Whether to look for function calls used as branches.
std::vector< BasicBlockPtr > basicBlocksSpanning(const AddressInterval &) const
Returns basic blocks that span an entire address interval.
Configuration & configuration()
Property: Configuration information.
AddressUsageMap aum(const FunctionPtr &) const
Returns the address usage map for a single function.
std::vector< FunctionPaddingMatcherPtr > FunctionPaddingMatchers
See functionPaddingMatchers.
SgAsmGenericSection * elfGot(SgAsmElfFileHeader *)
Find the ELF global offset table and save its address.
std::vector< Address > basicBlockConcreteSuccessors(const BasicBlockPtr &, bool *isComplete=NULL) const
Determines concrete successors for a basic block.
std::vector< DataBlockPtr > dataBlocksSpanning(const AddressInterval &) const
Returns data blocks that span an entire address interval.
DataBlockPtr findBestDataBlock(const AddressInterval &) const
Find an existing data block.
void forgetStackDeltas() const
Clears all cached stack deltas.
void allFunctionStackDelta() const
Compute stack delta analysis for all functions.
bool assumeFunctionsReturn() const
Property: Assume (or not) that function calls return.
static std::string basicBlockName(const BasicBlockPtr &)
Name of a basic block.
void unparse(std::ostream &, const BasicBlockPtr &) const
Unparse some entity.
FunctionPtr functionExists(Address entryVa) const
Determines whether a function exists in the CFG/AUM.
AddressIntervalSet basicBlockDataExtent(const BasicBlockPtr &) const
Returns the addresses used by basic block data.
size_t nPlaceholders() const
Returns the number of basic basic block placeholders in the CFG.
AddressIntervalSet functionExtent(const FunctionPtr &) const
Returns the addresses used by a function.
std::vector< BasicBlockPtr > basicBlocks() const
Returns all basic blocks attached to the CFG.
bool isEdgeInterProcedural(const ControlFlowGraph::Edge &edge, const FunctionPtr &sourceFunction) const
Determine if an edge is inter-procedural.
size_t nFunctions() const
Returns the number of functions attached to the CFG/AUM.
std::vector< FunctionPtr > discoverCalledFunctions() const
Scans the CFG to find function calls.
bool isEdgeIntraProcedural(ControlFlowGraph::ConstEdgeIterator edge) const
Determine if an edge is intra-procedural.
BasicBlockPtr basicBlockExists(const BasicBlockPtr &) const
Determines whether a discovered basic block exists in the CFG/AUM.
void settings(const BasePartitionerSettings &)
Partitioner settings.
std::set< Address > ghostSuccessors() const
Determine all ghost successors in the control flow graph.
bool autoAddCallReturnEdges() const
Property: Insert (or not) function call return edges.
Architecture::BaseConstPtr architecture() const
Property: Architecture information.
void unparse(std::ostream &, SgAsmInstruction *) const
Unparse some entity.
std::set< Address > functionGhostSuccessors(const FunctionPtr &) const
Returns ghost successors for a single function.
bool isEdgeInterProcedural(const ControlFlowGraph::Edge &edge, const FunctionPtr &sourceFunction, const FunctionPtr &targetFunction) const
Determine if an edge is inter-procedural.
std::string edgeName(const ControlFlowGraph::ConstEdgeIterator &) const
Name of an edge.
void unparse(std::ostream &, const FunctionPtr &) const
Unparse some entity.
ControlFlowGraph::VertexIterator indeterminateVertex()
Returns the special "indeterminate" vertex.
bool isEdgeIntraProcedural(const ControlFlowGraph::Edge &edge, const FunctionPtr &) const
Determine if an edge is intra-procedural.
ControlFlowGraph::ConstVertexIterator instructionVertex(Address insnVa) const
Returns the CFG vertex containing specified instruction.
size_t nBytes() const
Returns the number of bytes represented by the CFG.
BasicBlockPtr basicBlockContainingInstruction(Address insnVa) const
Returns the basic block that contains a specific instruction address.
bool basicBlockIsFunctionCall(const BasicBlockPtr &, Precision::Level precision=Precision::HIGH) const
Determine if a basic block looks like a function call.
void attachBasicBlock(const ControlFlowGraph::ConstVertexIterator &placeholder, const BasicBlockPtr &)
Attach a basic block to the CFG/AUM.
InstructionSemantics::BaseSemantics::RiscOperatorsPtr newOperators(SemanticMemoryParadigm) const
Obtain new RiscOperators.
void basicBlockMayReturnReset() const
Clear all may-return properties.
BasicBlockPtr detachBasicBlock(Address startVa)
Detach a basic block from the CFG/AUM.
const std::string & addressName(Address) const
Property: Name for address.
void discoverFunctionBasicBlocks(const FunctionPtr &function) const
Adds basic blocks to a function.
IndirectControlFlow::State & icf()
Internal data structures for indirect control flow recovery.
const CallingConvention::Analysis & functionCallingConvention(const FunctionPtr &) const
Calling convention analysis for one function.
bool usingSymbolicSemantics() const
Use or not use symbolic semantics.
std::vector< FunctionPtr > functionsOwningBasicBlocks(const Container &bblocks) const
Finds functions that own the specified basic block.
bool checkingCallBranch() const
Property: Whether to look for function calls used as branches.
void cfgGraphViz(std::ostream &, const AddressInterval &restrict=AddressInterval::whole(), bool showNeighbors=true) const
Output CFG as GraphViz.
const BasicBlockCallbacks & basicBlockCallbacks() const
Callbacks for adjusting basic block during discovery.
std::vector< SgAsmInstruction * > instructionsSpanning(const AddressInterval &) const
Returns instructions that span an entire address interval.
AddressUser instructionExists(Address startVa) const
Determines whether an instruction is attached to the CFG/AUM.
ControlFlowGraph::VertexIterator findPlaceholder(Address startVa)
Find the CFG vertex for a basic block placeholder.
void secondaryPartitioner(const PartitionerPtr &)
Property: Optional secondary partitioner.
static std::string functionName(const FunctionPtr &)
Name of a function.
std::vector< FunctionPtr > functionsOwningBasicBlock(const BasicBlockPtr &, bool doSort=true) const
Finds functions that own the specified basic block.
void expandIndeterminateCalls()
Expands indeterminate function calls.
BasicBlockPtr discoverBasicBlock(Address startVa) const
Discover instructions for a detached basic block.
void unparse(std::ostream &) const
Unparse some entity.
bool isEdgeIntraProcedural(const ControlFlowGraph::Edge &edge) const
Determine if an edge is intra-procedural.
DataBlockPtr attachDataBlock(const DataBlockPtr &)
Attach a data block to the CFG/AUM.
size_t attachFunctionBasicBlocks(const FunctionPtr &)
Create placeholders for function basic blocks.
void dumpCfg(std::ostream &, const std::string &prefix="", bool showBlocks=true, bool computeProperties=true) const
Output the control flow graph.
InstructionSemantics::BaseSemantics::RiscOperatorsPtr newOperators() const
Obtain new RiscOperators.
void assumeFunctionsReturn(bool)
Property: Assume (or not) that function calls return.
DataBlockPtr dataBlockExists(const DataBlockPtr &) const
Determine if a data block or its equivalent is attached to the CFG/AUM.
DataBlockPtr attachDataBlockToBasicBlock(const DataBlockPtr &, const BasicBlockPtr &)
Attach a data block to a basic block.
bool basicBlockSemanticsAutoDrop() const
Property: Automatically drop semantics for attached basic blocks.
std::vector< AddressUser > users(Address) const
Entities that exist at a particular address.
std::vector< DataBlockPtr > dataBlocksOverlapping(const AddressInterval &) const
Returns data blocks that overlap with specified address interval.
Partitioner(BOOST_RV_REF(Partitioner))
Move constructor.
BasicBlockPtr detachBasicBlock(const BasicBlockPtr &basicBlock)
Detach a basic block from the CFG/AUM.
std::vector< FunctionPtr > nextFunctionPrologue(Address startVa)
Finds the next function by searching for a function prologue.
InstructionSemantics::BaseSemantics::DispatcherPtr newDispatcher(const InstructionSemantics::BaseSemantics::RiscOperatorsPtr &) const
Obtain a new instruction semantics dispatcher.
std::vector< BasicBlockPtr > basicBlocksOverlapping(const AddressInterval &) const
Returns basic blocks that overlap with specified address interval.
void attachBasicBlock(const BasicBlockPtr &)
Attach a basic block to the CFG/AUM.
SgAsmInterpretation * interpretation() const
Property: Interpretation corresponding to the memory map.
std::string unparsePlain(SgAsmInstruction *) const
Unparse an instruction in a plain way.
Progress::Ptr progress() const
Property: How to report progress.
void detachFunction(const FunctionPtr &)
Detaches a function from the CFG/AUM.
PartitionerPtr secondaryPartitioner()
Property: Optional secondary partitioner.
static std::string vertexNameEnd(const ControlFlowGraph::Vertex &)
Name of last instruction in vertex.
void insnUnparser(const Unparser::BasePtr &)
Returns an unparser.
bool addressIsExecutable(Address) const
Returns true if address is executable.
void detachDataBlock(const DataBlockPtr &)
Detaches a data block from the CFG/AUM.
std::string vertexName(const ControlFlowGraph::ConstVertexIterator &) const
Name of a vertex.
void showStatistics() const
Print some partitioner performance statistics.
static Ptr instance(const Architecture::BaseConstPtr &)
Default allocating constructor.
void disableSymbolicSemantics()
Use or not use symbolic semantics.
const AddressUsageMap & aum() const
Returns the address usage map.
const IndirectControlFlow::State & icf() const
Internal data structures for indirect control flow recovery.
std::set< Address > basicBlockGhostSuccessors(const BasicBlockPtr &) const
Determine ghost successors for a basic block.
std::vector< FunctionPtr > functions() const
All functions attached to the CFG/AUM.
BasicBlockPtr erasePlaceholder(const ControlFlowGraph::ConstVertexIterator &placeholder)
Remove a basic block placeholder from the CFG/AUM.
void progress(const Progress::Ptr &)
Property: How to report progress.
std::vector< FunctionPtr > functionsSpanning(const AddressInterval &) const
Returns functions that span an entire address interval.
std::vector< SgAsmInstruction * > instructionsOverlapping(const AddressInterval &) const
Returns instructions that overlap with specified address interval.
void enableSymbolicSemantics(bool=true)
Use or not use symbolic semantics.
ControlFlowGraph::ConstVertexIterator findPlaceholder(Address startVa) const
Find the CFG vertex for a basic block placeholder.
const FunctionPrologueMatchers & functionPrologueMatchers() const
Ordered list of function prologue matchers.
Sawyer::Optional< Address > elfGotVa() const
Returns a previously cached ELF GOT address.
Sawyer::Container::Map< Address, std::string > AddressNameMap
Map address to name.
size_t nInstructions() const
Returns the number of instructions attached to the CFG/AUM.
void unparser(const Unparser::BasePtr &)
Returns an unparser.
static Ptr instance(const Architecture::BaseConstPtr &, const MemoryMap::Ptr &)
Construct a partitioner.
void autoAddCallReturnEdges(bool)
Property: Insert (or not) function call return edges.
InstructionSemantics::BaseSemantics::SValuePtr basicBlockStackDeltaOut(const BasicBlockPtr &, const FunctionPtr &function) const
Return the stack delta expression.
void clear()
Reset CFG/AUM to initial state.
BasicBlockPtr discoverBasicBlock(const ControlFlowGraph::ConstVertexIterator &placeholder) const
Discover instructions for a detached basic block.
std::vector< FunctionPtr > nextFunctionPrologue(Address startVa, Address &lastSearchedVa)
Finds the next function by searching for a function prologue.
bool isDefaultConstructed() const
Return true if this is a default constructed partitioner.
void allFunctionMayReturn() const
Compute may-return analysis for all functions.
std::vector< FunctionPrologueMatcherPtr > FunctionPrologueMatchers
See functionPrologueMatchers.
Unparser::BasePtr insnUnparser() const
Returns an unparser.
SmtSolverPtr smtSolver() const
SMT solver.
std::vector< FunctionPtr > functionsOwningBasicBlock(const ControlFlowGraph::Vertex &, bool doSort=true) const
Finds functions that own the specified basic block.
bool isEdgeIntraProcedural(ControlFlowGraph::ConstEdgeIterator edge, const FunctionPtr &) const
Determine if an edge is intra-procedural.
FunctionPtr attachOrMergeFunction(const FunctionPtr &)
Attaches or merges a function into the CFG/AUM.
DataBlockPtr attachDataBlockToFunction(const DataBlockPtr &, const FunctionPtr &)
Attach a data block to an attached or detached function.
BasicBlockPtr basicBlockExists(Address startVa) const
Determines whether a discovered basic block exists in the CFG/AUM.
size_t attachFunctions(const Functions &)
Attaches a function to the CFG/AUM.
BasicBlockPtr detachBasicBlock(const ControlFlowGraph::ConstVertexIterator &placeholder)
Detach a basic block from the CFG/AUM.
std::set< Address > functionDataFlowConstants(const FunctionPtr &) const
Find constants in function using data-flow.
void functionBasicBlockExtent(const FunctionPtr &function, AddressIntervalSet &retval) const
Returns the addresses used by a function.
size_t nBasicBlocks() const
Returns the number of basic blocks attached to the CFG/AUM.
const AddressNameMap & addressNames() const
Property: Name for address.
std::string edgeNameDst(const ControlFlowGraph::ConstEdgeIterator &) const
Name of an outgoing edge.
void configureInsnUnparser(const Unparser::BasePtr &) const
Configure the single-instruction unparser.
CallingConvention::Dictionary functionCallingConventionDefinitions(const FunctionPtr &) const
Return list of matching calling conventions.
bool basicBlockPopsStack(const BasicBlockPtr &) const
Determine if the basic block pops at least one byte from the stack.
std::vector< FunctionPtr > functionsOwningBasicBlock(const ControlFlowGraph::ConstVertexIterator &, bool doSort=true) const
Finds functions that own the specified basic block.
void fixInterFunctionEdges()
Adjust inter-function edge types.
void allFunctionIsNoop() const
Analyze all functions for whether they are effectivly no-ops.
std::vector< DataBlockPtr > dataBlocks() const
Returns the list of all attached data blocks.
void functionDataBlockExtent(const FunctionPtr &function, AddressIntervalSet &retval) const
Returns the addresses used by a function.
bool isEdgeInterProcedural(ControlFlowGraph::ConstEdgeIterator edge, const FunctionPtr &sourceFunction, const FunctionPtr &targetFunction) const
Determine if an edge is inter-procedural.
bool placeholderExists(Address startVa) const
Determines whether a basic block placeholder exists in the CFG.
const FunctionPaddingMatchers & functionPaddingMatchers() const
Ordered list of function padding matchers.
static PartitionerPtr instanceFromRbaFile(const boost::filesystem::path &, Serialization::Format=Serialization::BINARY)
Construct a partitioner by loading it and an AST from a file.
std::string edgeNameSrc(const ControlFlowGraph::ConstEdgeIterator &) const
Name of an incoming edge.
static std::string vertexName(const ControlFlowGraph::Vertex &)
Name of a vertex.
void semanticMemoryParadigm(SemanticMemoryParadigm)
Property: Whether to use map- or list-based memory states.
BasicBlockCallbacks & basicBlockCallbacks()
Callbacks for adjusting basic block during discovery.
FunctionPtr functionExists(const BasicBlockPtr &entryBlock) const
Determines whether a function exists in the CFG/AUM.
AddressIntervalSet functionDataBlockExtent(const FunctionPtr &function) const
Returns the addresses used by a function.
InstructionProvider & instructionProvider()
Returns the instruction provider.
Sawyer::Callbacks< BasicBlockCallbackPtr > BasicBlockCallbacks
See basicBlockCallbacks.
void sourceLocations(const SourceLocations &)
Property: Source locations.
size_t attachFunction(const FunctionPtr &)
Attaches a function to the CFG/AUM.
void forgetFunctionIsNoop(const FunctionPtr &) const
Clears cached function no-op analysis results.
static std::string edgeName(const ControlFlowGraph::Edge &)
Name of an edge.
static std::string edgeNameDst(const ControlFlowGraph::Edge &)
Name of an outgoing edge.
const CfgAdjustmentCallbacks & cfgAdjustmentCallbacks() const
List of all callbacks invoked when the CFG is adjusted.
void functionExtent(const FunctionPtr &function, AddressIntervalSet &retval) const
Returns the addresses used by a function.
AddressInterval instructionExtent(SgAsmInstruction *) const
Returns the address interval for an instruction.
void basicBlockSemanticsAutoDrop(bool)
Property: Automatically drop semantics for attached basic blocks.
MemoryMap::Ptr memoryMap() const
Returns the memory map.
CrossReferences instructionCrossReferences(const AddressIntervalSet &restriction) const
Cross references.
bool isEdgeInterProcedural(ControlFlowGraph::ConstEdgeIterator edge, const FunctionPtr &sourceFunction) const
Determine if an edge is inter-procedural.
std::vector< FunctionPtr > functionsContainedIn(const AddressInterval &) const
Returns functions that are fully contained in an address interval.
std::vector< FunctionPtr > discoverFunctionEntryVertices() const
Scans the CFG to find function entry basic blocks.
void allFunctionCallingConventionDefinition(const CallingConvention::Definition::Ptr &) const
Analyzes calling conventions and saves results.
SourceLocations & sourceLocations()
Property: Source locations.
bool isEdgeInterProcedural(const ControlFlowGraph::Edge &edge) const
Determine if an edge is inter-procedural.
AddressIntervalSet functionBasicBlockExtent(const FunctionPtr &function) const
Returns the addresses used by a function.
std::vector< FunctionPtr > functionsOwningBasicBlock(Address bblockVa, bool doSort=true) const
Finds functions that own the specified basic block.
const InstructionProvider & instructionProvider() const
Returns the instruction provider.
FunctionPaddingMatchers & functionPaddingMatchers()
Ordered list of function padding matchers.
Sawyer::Optional< bool > basicBlockOptionalMayReturn(const ControlFlowGraph::ConstVertexIterator &) const
Determine if part of the CFG can pop the top stack frame.
const BasePartitionerSettings & settings() const
Partitioner settings.
static std::string edgeNameSrc(const ControlFlowGraph::Edge &)
Name of an incoming edge.
void saveAsRbaFile(const boost::filesystem::path &name, Serialization::Format fmt) const
Save this partitioner as an RBA file.
ControlFlowGraph::ConstVertexIterator undiscoveredVertex() const
Returns the special "undiscovered" vertex.
std::string unparse(SgAsmInstruction *) const
Unparse some entity.
void updateProgress(const std::string &phase, double completion) const
Update partitioner with a new progress report.
CallingConvention::Dictionary functionCallingConventionDefinitions(const FunctionPtr &, const CallingConvention::Definition::Ptr &) const
Return list of matching calling conventions.
void allFunctionCallingConventionDefinition() const
Analyzes calling conventions and saves results.
AddressInterval dataBlockExtent(const DataBlockPtr &) const
Returns the addresses used by a data block.
InstructionSemantics::BaseSemantics::SValuePtr basicBlockStackDeltaIn(const BasicBlockPtr &, const FunctionPtr &function) const
Return the stack delta expression.
AddressUser instructionExists(SgAsmInstruction *insn) const
Determines whether an instruction is attached to the CFG/AUM.
Bidirectional mapping between addresses and source locations.
API and storage for attributes.
Definition Attribute.h:215
Container associating values with keys.
Definition Sawyer/Map.h:72
Holds a value or nothing.
Definition Optional.h:54
Creates SharedPointer from this.
Base class for reference counted objects.
Represents the file header of an ELF binary container.
Contiguous region of a file.
Base class for machine instructions.
Represents an interpretation of a binary container.
std::shared_ptr< const Base > BaseConstPtr
Reference counted pointer for Architecture::Base.
std::vector< DefinitionPtr > Dictionary
An ordered collection of calling convention definitions.
boost::shared_ptr< RiscOperators > RiscOperatorsPtr
Shared-ownership pointer to a RISC operators object.
boost::shared_ptr< Dispatcher > DispatcherPtr
Shared-ownership pointer to a semantics instruction dispatcher.
std::vector< BasicBlockSuccessor > BasicBlockSuccessors
All successors in no particular order.
std::uint64_t Address
Address.
Definition Address.h:11
std::shared_ptr< SmtSolver > SmtSolverPtr
Reference counting pointer.
The ROSE library.
Represents information about a thunk.
Address target
The one and only successor for the basic block.
BasicBlockPtr bblock
The one and only basic block for the thunk.