diff options
Diffstat (limited to 'lib/MC/MCDisassembler')
-rw-r--r-- | lib/MC/MCDisassembler/Android.mk | 26 | ||||
-rw-r--r-- | lib/MC/MCDisassembler/CMakeLists.txt | 3 | ||||
-rw-r--r-- | lib/MC/MCDisassembler/Disassembler.cpp | 65 | ||||
-rw-r--r-- | lib/MC/MCDisassembler/Disassembler.h | 4 | ||||
-rw-r--r-- | lib/MC/MCDisassembler/MCDisassembler.cpp | 39 | ||||
-rw-r--r-- | lib/MC/MCDisassembler/MCExternalSymbolizer.cpp | 198 | ||||
-rw-r--r-- | lib/MC/MCDisassembler/MCRelocationInfo.cpp | 39 |
7 files changed, 328 insertions, 46 deletions
diff --git a/lib/MC/MCDisassembler/Android.mk b/lib/MC/MCDisassembler/Android.mk index 7f73df3..87455e2 100644 --- a/lib/MC/MCDisassembler/Android.mk +++ b/lib/MC/MCDisassembler/Android.mk @@ -1,15 +1,37 @@ LOCAL_PATH:= $(call my-dir) +mc_disassembler_SRC_FILES := \ + Disassembler.cpp \ + MCDisassembler.cpp \ + MCExternalSymbolizer.cpp \ + MCRelocationInfo.cpp + + # For the host # ===================================================== include $(CLEAR_VARS) -LOCAL_SRC_FILES := \ - Disassembler.cpp +LOCAL_SRC_FILES := $(mc_disassembler_SRC_FILES) LOCAL_MODULE:= libLLVMMCDisassembler LOCAL_MODULE_TAGS := optional + include $(LLVM_HOST_BUILD_MK) include $(BUILD_HOST_STATIC_LIBRARY) + +# For the device +# ===================================================== +include $(CLEAR_VARS) +ifneq (true,$(DISABLE_LLVM_DEVICE_BUILDS)) + +LOCAL_SRC_FILES := $(mc_disassembler_SRC_FILES) + +LOCAL_MODULE:= libLLVMMCDisassembler + +LOCAL_MODULE_TAGS := optional + +include $(LLVM_DEVICE_BUILD_MK) +include $(BUILD_STATIC_LIBRARY) +endif diff --git a/lib/MC/MCDisassembler/CMakeLists.txt b/lib/MC/MCDisassembler/CMakeLists.txt index 5195b9e..f266f8f 100644 --- a/lib/MC/MCDisassembler/CMakeLists.txt +++ b/lib/MC/MCDisassembler/CMakeLists.txt @@ -1,3 +1,6 @@ add_llvm_library(LLVMMCDisassembler Disassembler.cpp + MCRelocationInfo.cpp + MCExternalSymbolizer.cpp + MCDisassembler.cpp ) diff --git a/lib/MC/MCDisassembler/Disassembler.cpp b/lib/MC/MCDisassembler/Disassembler.cpp index 0530c26..d0d7f30 100644 --- a/lib/MC/MCDisassembler/Disassembler.cpp +++ b/lib/MC/MCDisassembler/Disassembler.cpp @@ -21,7 +21,6 @@ #include "llvm/MC/MCSymbolizer.h" #include "llvm/Support/ErrorHandling.h" #include "llvm/Support/FormattedStream.h" -#include "llvm/Support/MemoryObject.h" #include "llvm/Support/TargetRegistry.h" using namespace llvm; @@ -33,10 +32,11 @@ using namespace llvm; // functions can all be passed as NULL. If successful, this returns a // disassembler context. If not, it returns NULL. // -LLVMDisasmContextRef LLVMCreateDisasmCPU(const char *Triple, const char *CPU, - void *DisInfo, int TagType, - LLVMOpInfoCallback GetOpInfo, - LLVMSymbolLookupCallback SymbolLookUp){ +LLVMDisasmContextRef +LLVMCreateDisasmCPUFeatures(const char *Triple, const char *CPU, + const char *Features, void *DisInfo, int TagType, + LLVMOpInfoCallback GetOpInfo, + LLVMSymbolLookupCallback SymbolLookUp) { // Get the target. std::string Error; const Target *TheTarget = TargetRegistry::lookupTarget(Triple, Error); @@ -56,11 +56,8 @@ LLVMDisasmContextRef LLVMCreateDisasmCPU(const char *Triple, const char *CPU, if (!MII) return nullptr; - // Package up features to be passed to target/subtarget - std::string FeaturesStr; - const MCSubtargetInfo *STI = TheTarget->createMCSubtargetInfo(Triple, CPU, - FeaturesStr); + Features); if (!STI) return nullptr; @@ -101,11 +98,19 @@ LLVMDisasmContextRef LLVMCreateDisasmCPU(const char *Triple, const char *CPU, return DC; } +LLVMDisasmContextRef LLVMCreateDisasmCPU(const char *Triple, const char *CPU, + void *DisInfo, int TagType, + LLVMOpInfoCallback GetOpInfo, + LLVMSymbolLookupCallback SymbolLookUp){ + return LLVMCreateDisasmCPUFeatures(Triple, CPU, "", DisInfo, TagType, + GetOpInfo, SymbolLookUp); +} + LLVMDisasmContextRef LLVMCreateDisasm(const char *Triple, void *DisInfo, int TagType, LLVMOpInfoCallback GetOpInfo, LLVMSymbolLookupCallback SymbolLookUp) { - return LLVMCreateDisasmCPU(Triple, "", DisInfo, TagType, GetOpInfo, - SymbolLookUp); + return LLVMCreateDisasmCPUFeatures(Triple, "", "", DisInfo, TagType, + GetOpInfo, SymbolLookUp); } // @@ -116,30 +121,6 @@ void LLVMDisasmDispose(LLVMDisasmContextRef DCR){ delete DC; } -namespace { -// -// The memory object created by LLVMDisasmInstruction(). -// -class DisasmMemoryObject : public MemoryObject { - uint8_t *Bytes; - uint64_t Size; - uint64_t BasePC; -public: - DisasmMemoryObject(uint8_t *bytes, uint64_t size, uint64_t basePC) : - Bytes(bytes), Size(size), BasePC(basePC) {} - - uint64_t getBase() const override { return BasePC; } - uint64_t getExtent() const override { return Size; } - - int readByte(uint64_t Addr, uint8_t *Byte) const override { - if (Addr - BasePC >= Size) - return -1; - *Byte = Bytes[Addr - BasePC]; - return 0; - } -}; -} // end anonymous namespace - /// \brief Emits the comments that are stored in \p DC comment stream. /// Each comment in the comment stream must end with a newline. static void emitComments(LLVMDisasmContext *DC, @@ -202,19 +183,19 @@ static int getItineraryLatency(LLVMDisasmContext *DC, const MCInst &Inst) { static int getLatency(LLVMDisasmContext *DC, const MCInst &Inst) { // Try to compute scheduling information. const MCSubtargetInfo *STI = DC->getSubtargetInfo(); - const MCSchedModel *SCModel = STI->getSchedModel(); + const MCSchedModel SCModel = STI->getSchedModel(); const int NoInformationAvailable = -1; // Check if we have a scheduling model for instructions. - if (!SCModel || !SCModel->hasInstrSchedModel()) - // Try to fall back to the itinerary model if we do not have a - // scheduling model. + if (!SCModel.hasInstrSchedModel()) + // Try to fall back to the itinerary model if the scheduling model doesn't + // have a scheduling table. Note the default does not have a table. return getItineraryLatency(DC, Inst); // Get the scheduling class of the requested instruction. const MCInstrDesc& Desc = DC->getInstrInfo()->get(Inst.getOpcode()); unsigned SCClass = Desc.getSchedClass(); - const MCSchedClassDesc *SCDesc = SCModel->getSchedClassDesc(SCClass); + const MCSchedClassDesc *SCDesc = SCModel.getSchedClassDesc(SCClass); // Resolving the variant SchedClass requires an MI to pass to // SubTargetInfo::resolveSchedClass. if (!SCDesc || !SCDesc->isValid() || SCDesc->isVariant()) @@ -263,7 +244,7 @@ size_t LLVMDisasmInstruction(LLVMDisasmContextRef DCR, uint8_t *Bytes, size_t OutStringSize){ LLVMDisasmContext *DC = (LLVMDisasmContext *)DCR; // Wrap the pointer to the Bytes, BytesSize and PC in a MemoryObject. - DisasmMemoryObject MemoryObject(Bytes, BytesSize, PC); + ArrayRef<uint8_t> Data(Bytes, BytesSize); uint64_t Size; MCInst Inst; @@ -272,7 +253,7 @@ size_t LLVMDisasmInstruction(LLVMDisasmContextRef DCR, uint8_t *Bytes, MCDisassembler::DecodeStatus S; SmallVector<char, 64> InsnStr; raw_svector_ostream Annotations(InsnStr); - S = DisAsm->getInstruction(Inst, Size, MemoryObject, PC, + S = DisAsm->getInstruction(Inst, Size, Data, PC, /*REMOVE*/ nulls(), Annotations); switch (S) { case MCDisassembler::Fail: diff --git a/lib/MC/MCDisassembler/Disassembler.h b/lib/MC/MCDisassembler/Disassembler.h index d1d40cd..46d0c4c 100644 --- a/lib/MC/MCDisassembler/Disassembler.h +++ b/lib/MC/MCDisassembler/Disassembler.h @@ -14,8 +14,8 @@ // //===----------------------------------------------------------------------===// -#ifndef LLVM_MC_DISASSEMBLER_H -#define LLVM_MC_DISASSEMBLER_H +#ifndef LLVM_LIB_MC_MCDISASSEMBLER_DISASSEMBLER_H +#define LLVM_LIB_MC_MCDISASSEMBLER_DISASSEMBLER_H #include "llvm-c/Disassembler.h" #include "llvm/ADT/SmallString.h" diff --git a/lib/MC/MCDisassembler/MCDisassembler.cpp b/lib/MC/MCDisassembler/MCDisassembler.cpp new file mode 100644 index 0000000..1084e5e --- /dev/null +++ b/lib/MC/MCDisassembler/MCDisassembler.cpp @@ -0,0 +1,39 @@ +//===-- MCDisassembler.cpp - Disassembler interface -----------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#include "llvm/MC/MCDisassembler.h" +#include "llvm/MC/MCExternalSymbolizer.h" +#include "llvm/Support/raw_ostream.h" + +using namespace llvm; + +MCDisassembler::~MCDisassembler() { +} + +bool MCDisassembler::tryAddingSymbolicOperand(MCInst &Inst, int64_t Value, + uint64_t Address, bool IsBranch, + uint64_t Offset, + uint64_t InstSize) const { + raw_ostream &cStream = CommentStream ? *CommentStream : nulls(); + if (Symbolizer) + return Symbolizer->tryAddingSymbolicOperand(Inst, cStream, Value, Address, + IsBranch, Offset, InstSize); + return false; +} + +void MCDisassembler::tryAddingPcLoadReferenceComment(int64_t Value, + uint64_t Address) const { + raw_ostream &cStream = CommentStream ? *CommentStream : nulls(); + if (Symbolizer) + Symbolizer->tryAddingPcLoadReferenceComment(cStream, Value, Address); +} + +void MCDisassembler::setSymbolizer(std::unique_ptr<MCSymbolizer> Symzer) { + Symbolizer = std::move(Symzer); +} diff --git a/lib/MC/MCDisassembler/MCExternalSymbolizer.cpp b/lib/MC/MCDisassembler/MCExternalSymbolizer.cpp new file mode 100644 index 0000000..0145623 --- /dev/null +++ b/lib/MC/MCDisassembler/MCExternalSymbolizer.cpp @@ -0,0 +1,198 @@ +//===-- MCExternalSymbolizer.cpp - External symbolizer --------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#include "llvm/MC/MCExternalSymbolizer.h" +#include "llvm/MC/MCContext.h" +#include "llvm/MC/MCExpr.h" +#include "llvm/MC/MCInst.h" +#include "llvm/Support/raw_ostream.h" +#include <cstring> + +using namespace llvm; + +// This function tries to add a symbolic operand in place of the immediate +// Value in the MCInst. The immediate Value has had any PC adjustment made by +// the caller. If the instruction is a branch instruction then IsBranch is true, +// else false. If the getOpInfo() function was set as part of the +// setupForSymbolicDisassembly() call then that function is called to get any +// symbolic information at the Address for this instruction. If that returns +// non-zero then the symbolic information it returns is used to create an MCExpr +// and that is added as an operand to the MCInst. If getOpInfo() returns zero +// and IsBranch is true then a symbol look up for Value is done and if a symbol +// is found an MCExpr is created with that, else an MCExpr with Value is +// created. This function returns true if it adds an operand to the MCInst and +// false otherwise. +bool MCExternalSymbolizer::tryAddingSymbolicOperand(MCInst &MI, + raw_ostream &cStream, + int64_t Value, + uint64_t Address, + bool IsBranch, + uint64_t Offset, + uint64_t InstSize) { + struct LLVMOpInfo1 SymbolicOp; + std::memset(&SymbolicOp, '\0', sizeof(struct LLVMOpInfo1)); + SymbolicOp.Value = Value; + + if (!GetOpInfo || + !GetOpInfo(DisInfo, Address, Offset, InstSize, 1, &SymbolicOp)) { + // Clear SymbolicOp.Value from above and also all other fields. + std::memset(&SymbolicOp, '\0', sizeof(struct LLVMOpInfo1)); + + // At this point, GetOpInfo() did not find any relocation information about + // this operand and we are left to use the SymbolLookUp() call back to guess + // if the Value is the address of a symbol. In the case this is a branch + // that always makes sense to guess. But in the case of an immediate it is + // a bit more questionable if it is an address of a symbol or some other + // reference. So if the immediate Value comes from a width of 1 byte, + // InstSize, we will not guess it is an address of a symbol. Because in + // object files assembled starting at address 0 this usually leads to + // incorrect symbolication. + if (!SymbolLookUp || (InstSize == 1 && !IsBranch)) + return false; + + uint64_t ReferenceType; + if (IsBranch) + ReferenceType = LLVMDisassembler_ReferenceType_In_Branch; + else + ReferenceType = LLVMDisassembler_ReferenceType_InOut_None; + const char *ReferenceName; + const char *Name = SymbolLookUp(DisInfo, Value, &ReferenceType, Address, + &ReferenceName); + if (Name) { + SymbolicOp.AddSymbol.Name = Name; + SymbolicOp.AddSymbol.Present = true; + // If Name is a C++ symbol name put the human readable name in a comment. + if(ReferenceType == LLVMDisassembler_ReferenceType_DeMangled_Name) + cStream << ReferenceName; + } + // For branches always create an MCExpr so it gets printed as hex address. + else if (IsBranch) { + SymbolicOp.Value = Value; + } + if(ReferenceType == LLVMDisassembler_ReferenceType_Out_SymbolStub) + cStream << "symbol stub for: " << ReferenceName; + else if(ReferenceType == LLVMDisassembler_ReferenceType_Out_Objc_Message) + cStream << "Objc message: " << ReferenceName; + if (!Name && !IsBranch) + return false; + } + + const MCExpr *Add = nullptr; + if (SymbolicOp.AddSymbol.Present) { + if (SymbolicOp.AddSymbol.Name) { + StringRef Name(SymbolicOp.AddSymbol.Name); + MCSymbol *Sym = Ctx.GetOrCreateSymbol(Name); + Add = MCSymbolRefExpr::Create(Sym, Ctx); + } else { + Add = MCConstantExpr::Create((int)SymbolicOp.AddSymbol.Value, Ctx); + } + } + + const MCExpr *Sub = nullptr; + if (SymbolicOp.SubtractSymbol.Present) { + if (SymbolicOp.SubtractSymbol.Name) { + StringRef Name(SymbolicOp.SubtractSymbol.Name); + MCSymbol *Sym = Ctx.GetOrCreateSymbol(Name); + Sub = MCSymbolRefExpr::Create(Sym, Ctx); + } else { + Sub = MCConstantExpr::Create((int)SymbolicOp.SubtractSymbol.Value, Ctx); + } + } + + const MCExpr *Off = nullptr; + if (SymbolicOp.Value != 0) + Off = MCConstantExpr::Create(SymbolicOp.Value, Ctx); + + const MCExpr *Expr; + if (Sub) { + const MCExpr *LHS; + if (Add) + LHS = MCBinaryExpr::CreateSub(Add, Sub, Ctx); + else + LHS = MCUnaryExpr::CreateMinus(Sub, Ctx); + if (Off) + Expr = MCBinaryExpr::CreateAdd(LHS, Off, Ctx); + else + Expr = LHS; + } else if (Add) { + if (Off) + Expr = MCBinaryExpr::CreateAdd(Add, Off, Ctx); + else + Expr = Add; + } else { + if (Off) + Expr = Off; + else + Expr = MCConstantExpr::Create(0, Ctx); + } + + Expr = RelInfo->createExprForCAPIVariantKind(Expr, SymbolicOp.VariantKind); + if (!Expr) + return false; + + MI.addOperand(MCOperand::CreateExpr(Expr)); + return true; +} + +// This function tries to add a comment as to what is being referenced by a load +// instruction with the base register that is the Pc. These can often be values +// in a literal pool near the Address of the instruction. The Address of the +// instruction and its immediate Value are used as a possible literal pool entry. +// The SymbolLookUp call back will return the name of a symbol referenced by the +// literal pool's entry if the referenced address is that of a symbol. Or it +// will return a pointer to a literal 'C' string if the referenced address of +// the literal pool's entry is an address into a section with C string literals. +// Or if the reference is to an Objective-C data structure it will return a +// specific reference type for it and a string. +void MCExternalSymbolizer::tryAddingPcLoadReferenceComment(raw_ostream &cStream, + int64_t Value, + uint64_t Address) { + if (SymbolLookUp) { + uint64_t ReferenceType = LLVMDisassembler_ReferenceType_In_PCrel_Load; + const char *ReferenceName; + (void)SymbolLookUp(DisInfo, Value, &ReferenceType, Address, &ReferenceName); + if(ReferenceType == LLVMDisassembler_ReferenceType_Out_LitPool_SymAddr) + cStream << "literal pool symbol address: " << ReferenceName; + else if(ReferenceType == + LLVMDisassembler_ReferenceType_Out_LitPool_CstrAddr) { + cStream << "literal pool for: \""; + cStream.write_escaped(ReferenceName); + cStream << "\""; + } + else if(ReferenceType == + LLVMDisassembler_ReferenceType_Out_Objc_CFString_Ref) + cStream << "Objc cfstring ref: @\"" << ReferenceName << "\""; + else if(ReferenceType == + LLVMDisassembler_ReferenceType_Out_Objc_Message) + cStream << "Objc message: " << ReferenceName; + else if(ReferenceType == + LLVMDisassembler_ReferenceType_Out_Objc_Message_Ref) + cStream << "Objc message ref: " << ReferenceName; + else if(ReferenceType == + LLVMDisassembler_ReferenceType_Out_Objc_Selector_Ref) + cStream << "Objc selector ref: " << ReferenceName; + else if(ReferenceType == + LLVMDisassembler_ReferenceType_Out_Objc_Class_Ref) + cStream << "Objc class ref: " << ReferenceName; + } +} + +namespace llvm { +MCSymbolizer *createMCSymbolizer(StringRef TT, LLVMOpInfoCallback GetOpInfo, + LLVMSymbolLookupCallback SymbolLookUp, + void *DisInfo, + MCContext *Ctx, + MCRelocationInfo *RelInfo) { + assert(Ctx && "No MCContext given for symbolic disassembly"); + + return new MCExternalSymbolizer(*Ctx, + std::unique_ptr<MCRelocationInfo>(RelInfo), + GetOpInfo, SymbolLookUp, DisInfo); +} +} diff --git a/lib/MC/MCDisassembler/MCRelocationInfo.cpp b/lib/MC/MCDisassembler/MCRelocationInfo.cpp new file mode 100644 index 0000000..ff0c27f --- /dev/null +++ b/lib/MC/MCDisassembler/MCRelocationInfo.cpp @@ -0,0 +1,39 @@ +//==-- MCRelocationInfo.cpp ------------------------------------------------==// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#include "llvm/MC/MCRelocationInfo.h" +#include "llvm-c/Disassembler.h" +#include "llvm/Object/ObjectFile.h" +#include "llvm/Support/TargetRegistry.h" + +using namespace llvm; + +MCRelocationInfo::MCRelocationInfo(MCContext &Ctx) + : Ctx(Ctx) { +} + +MCRelocationInfo::~MCRelocationInfo() { +} + +const MCExpr * +MCRelocationInfo::createExprForRelocation(object::RelocationRef Rel) { + return nullptr; +} + +const MCExpr * +MCRelocationInfo::createExprForCAPIVariantKind(const MCExpr *SubExpr, + unsigned VariantKind) { + if (VariantKind != LLVMDisassembler_VariantKind_None) + return nullptr; + return SubExpr; +} + +MCRelocationInfo *llvm::createMCRelocationInfo(StringRef TT, MCContext &Ctx) { + return new MCRelocationInfo(Ctx); +} |