Refactor data-in-code annotations.
Use a dedicated MachO load command to annotate data-in-code regions.
This is the same format the linker produces for final executable images,
allowing consistency of representation and use of introspection tools
for both object and executable files.
Data-in-code regions are annotated via ".data_region"/".end_data_region"
directive pairs, with an optional region type.
data_region_directive := ".data_region" { region_type }
region_type := "jt8" | "jt16" | "jt32" | "jta32"
end_data_region_directive := ".end_data_region"
The previous handling of ARM-style "$d.*" labels was broken and has
been removed. Specifically, it didn't handle ARM vs. Thumb mode when
marking the end of the section.
rdar://11459456
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157062 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/MC/MCAsmInfo.cpp b/lib/MC/MCAsmInfo.cpp
index 2456858..d9c1d51 100644
--- a/lib/MC/MCAsmInfo.cpp
+++ b/lib/MC/MCAsmInfo.cpp
@@ -50,6 +50,7 @@
AllowNameToStartWithDigit = false;
AllowPeriodsInName = true;
AllowUTF8 = true;
+ UseDataRegionDirectives = false;
ZeroDirective = "\t.zero\t";
AsciiDirective = "\t.ascii\t";
AscizDirective = "\t.asciz\t";
@@ -57,12 +58,6 @@
Data16bitsDirective = "\t.short\t";
Data32bitsDirective = "\t.long\t";
Data64bitsDirective = "\t.quad\t";
- DataBegin = "$d.";
- CodeBegin = "$a.";
- JT8Begin = "$d.";
- JT16Begin = "$d.";
- JT32Begin = "$d.";
- SupportsDataRegions = false;
SunStyleELFSectionSwitchSyntax = false;
UsesELFSectionDirectiveForBSS = false;
AlignDirective = "\t.align\t";
diff --git a/lib/MC/MCAsmInfoCOFF.cpp b/lib/MC/MCAsmInfoCOFF.cpp
index 8941365..678e75a 100644
--- a/lib/MC/MCAsmInfoCOFF.cpp
+++ b/lib/MC/MCAsmInfoCOFF.cpp
@@ -36,8 +36,6 @@
SupportsDebugInformation = true;
DwarfSectionOffsetDirective = "\t.secrel32\t";
HasMicrosoftFastStdCallMangling = true;
-
- SupportsDataRegions = false;
}
void MCAsmInfoMicrosoft::anchor() { }
diff --git a/lib/MC/MCAsmInfoDarwin.cpp b/lib/MC/MCAsmInfoDarwin.cpp
index 4d67592..73ef7ba 100644
--- a/lib/MC/MCAsmInfoDarwin.cpp
+++ b/lib/MC/MCAsmInfoDarwin.cpp
@@ -43,13 +43,6 @@
HasMachoTBSSDirective = true; // Uses .tbss
HasStaticCtorDtorReferenceInStaticMode = true;
- CodeBegin = "L$start$code$";
- DataBegin = "L$start$data$";
- JT8Begin = "L$start$jt8$";
- JT16Begin = "L$start$jt16$";
- JT32Begin = "L$start$jt32$";
- SupportsDataRegions = true;
-
// FIXME: Darwin 10 and newer don't need this.
LinkerRequiresNonEmptyDwarfLines = true;
diff --git a/lib/MC/MCAsmStreamer.cpp b/lib/MC/MCAsmStreamer.cpp
index 3ce84c2..9497b6b 100644
--- a/lib/MC/MCAsmStreamer.cpp
+++ b/lib/MC/MCAsmStreamer.cpp
@@ -138,6 +138,7 @@
virtual void EmitEHSymAttributes(const MCSymbol *Symbol,
MCSymbol *EHSymbol);
virtual void EmitAssemblerFlag(MCAssemblerFlag Flag);
+ virtual void EmitDataRegion(MCDataRegionType Kind);
virtual void EmitThumbFunc(MCSymbol *Func);
virtual void EmitAssignment(MCSymbol *Symbol, const MCExpr *Value);
@@ -352,6 +353,21 @@
EmitEOL();
}
+void MCAsmStreamer::EmitDataRegion(MCDataRegionType Kind) {
+ MCContext &Ctx = getContext();
+ const MCAsmInfo &MAI = Ctx.getAsmInfo();
+ if (!MAI.doesSupportDataRegionDirectives())
+ return;
+ switch (Kind) {
+ case MCDR_DataRegion: OS << "\t.data_region"; break;
+ case MCDR_DataRegionJT8: OS << "\t.data_region jt8"; break;
+ case MCDR_DataRegionJT16: OS << "\t.data_region jt16"; break;
+ case MCDR_DataRegionJT32: OS << "\t.data_region jt32"; break;
+ case MCDR_DataRegionEnd: OS << "\t.end_data_region"; break;
+ }
+ EmitEOL();
+}
+
void MCAsmStreamer::EmitThumbFunc(MCSymbol *Func) {
// This needs to emit to a temporary string to get properly quoted
// MCSymbols when they have spaces in them.
diff --git a/lib/MC/MCELFStreamer.cpp b/lib/MC/MCELFStreamer.cpp
index 6c4d0e3..6ac9d9d 100644
--- a/lib/MC/MCELFStreamer.cpp
+++ b/lib/MC/MCELFStreamer.cpp
@@ -13,6 +13,8 @@
#include "MCELF.h"
#include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/ADT/StringExtras.h"
+#include "llvm/ADT/Twine.h"
#include "llvm/MC/MCAssembler.h"
#include "llvm/MC/MCCodeEmitter.h"
#include "llvm/MC/MCContext.h"
diff --git a/lib/MC/MCMachOStreamer.cpp b/lib/MC/MCMachOStreamer.cpp
index bc6cf77..970aa8b 100644
--- a/lib/MC/MCMachOStreamer.cpp
+++ b/lib/MC/MCMachOStreamer.cpp
@@ -1,4 +1,3 @@
-//===- lib/MC/MCMachOStreamer.cpp - Mach-O Object Output ------------===//
//
// The LLVM Compiler Infrastructure
//
@@ -33,6 +32,8 @@
private:
virtual void EmitInstToData(const MCInst &Inst);
+ void EmitDataRegion(DataRegionData::KindTy Kind);
+ void EmitDataRegionEnd();
public:
MCMachOStreamer(MCContext &Context, MCAsmBackend &MAB,
raw_ostream &OS, MCCodeEmitter *Emitter)
@@ -46,6 +47,7 @@
virtual void EmitEHSymAttributes(const MCSymbol *Symbol,
MCSymbol *EHSymbol);
virtual void EmitAssemblerFlag(MCAssemblerFlag Flag);
+ virtual void EmitDataRegion(MCDataRegionType Kind);
virtual void EmitThumbFunc(MCSymbol *Func);
virtual void EmitAssignment(MCSymbol *Symbol, const MCExpr *Value);
virtual void EmitSymbolAttribute(MCSymbol *Symbol, MCSymbolAttr Attribute);
@@ -138,6 +140,26 @@
SD.setFlags(SD.getFlags() & ~SF_ReferenceTypeMask);
}
+void MCMachOStreamer::EmitDataRegion(DataRegionData::KindTy Kind) {
+ // Create a temporary label to mark the start of the data region.
+ MCSymbol *Start = getContext().CreateTempSymbol();
+ EmitLabel(Start);
+ // Record the region for the object writer to use.
+ DataRegionData Data = { Kind, Start, NULL };
+ std::vector<DataRegionData> &Regions = getAssembler().getDataRegions();
+ Regions.push_back(Data);
+}
+
+void MCMachOStreamer::EmitDataRegionEnd() {
+ std::vector<DataRegionData> &Regions = getAssembler().getDataRegions();
+ assert(Regions.size() && "Mismatched .end_data_region!");
+ DataRegionData &Data = Regions.back();
+ assert(Data.End == NULL && "Mismatched .end_data_region!");
+ // Create a temporary label to mark the end of the data region.
+ Data.End = getContext().CreateTempSymbol();
+ EmitLabel(Data.End);
+}
+
void MCMachOStreamer::EmitAssemblerFlag(MCAssemblerFlag Flag) {
// Let the target do whatever target specific stuff it needs to do.
getAssembler().getBackend().handleAssemblerFlag(Flag);
@@ -153,6 +175,26 @@
}
}
+void MCMachOStreamer::EmitDataRegion(MCDataRegionType Kind) {
+ switch (Kind) {
+ case MCDR_DataRegion:
+ EmitDataRegion(DataRegionData::Data);
+ return;
+ case MCDR_DataRegionJT8:
+ EmitDataRegion(DataRegionData::JumpTable8);
+ return;
+ case MCDR_DataRegionJT16:
+ EmitDataRegion(DataRegionData::JumpTable16);
+ return;
+ case MCDR_DataRegionJT32:
+ EmitDataRegion(DataRegionData::JumpTable32);
+ return;
+ case MCDR_DataRegionEnd:
+ EmitDataRegionEnd();
+ return;
+ }
+}
+
void MCMachOStreamer::EmitThumbFunc(MCSymbol *Symbol) {
// Remember that the function is a thumb function. Fixup and relocation
// values will need adjusted.
diff --git a/lib/MC/MCParser/DarwinAsmParser.cpp b/lib/MC/MCParser/DarwinAsmParser.cpp
index 6f45068..5662fea 100644
--- a/lib/MC/MCParser/DarwinAsmParser.cpp
+++ b/lib/MC/MCParser/DarwinAsmParser.cpp
@@ -14,6 +14,7 @@
#include "llvm/MC/MCSymbol.h"
#include "llvm/MC/MCParser/MCAsmLexer.h"
#include "llvm/MC/MCParser/MCAsmParser.h"
+#include "llvm/ADT/StringSwitch.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/Twine.h"
#include "llvm/Support/MemoryBuffer.h"
@@ -56,6 +57,9 @@
AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveTBSS>(".tbss");
AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveZerofill>(".zerofill");
+ AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveDataRegion>(".data_region");
+ AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveDataRegionEnd>(".end_data_region");
+
// Special section directives.
AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveConst>(".const");
AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveConstData>(".const_data");
@@ -113,6 +117,8 @@
bool ParseDirectiveSubsectionsViaSymbols(StringRef, SMLoc);
bool ParseDirectiveTBSS(StringRef, SMLoc);
bool ParseDirectiveZerofill(StringRef, SMLoc);
+ bool ParseDirectiveDataRegion(StringRef, SMLoc);
+ bool ParseDirectiveDataRegionEnd(StringRef, SMLoc);
// Named Section Directive
bool ParseSectionDirectiveConst(StringRef, SMLoc) {
@@ -659,6 +665,42 @@
return false;
}
+/// ParseDirectiveDataRegion
+/// ::= .data_region [ ( jt8 | jt16 | jt32 ) ]
+bool DarwinAsmParser::ParseDirectiveDataRegion(StringRef, SMLoc) {
+ if (getLexer().is(AsmToken::EndOfStatement)) {
+ Lex();
+ getStreamer().EmitDataRegion(MCDR_DataRegion);
+ return false;
+ }
+ StringRef RegionType;
+ SMLoc Loc = getParser().getTok().getLoc();
+ if (getParser().ParseIdentifier(RegionType))
+ return TokError("expected region type after '.data_region' directive");
+ int Kind = StringSwitch<int>(RegionType)
+ .Case("jt8", MCDR_DataRegionJT8)
+ .Case("jt16", MCDR_DataRegionJT16)
+ .Case("jt32", MCDR_DataRegionJT32)
+ .Default(-1);
+ if (Kind == -1)
+ return Error(Loc, "unknown region type in '.data_region' directive");
+ Lex();
+
+ getStreamer().EmitDataRegion((MCDataRegionType)Kind);
+ return false;
+}
+
+/// ParseDirectiveDataRegionEnd
+/// ::= .end_data_region
+bool DarwinAsmParser::ParseDirectiveDataRegionEnd(StringRef, SMLoc) {
+ if (getLexer().isNot(AsmToken::EndOfStatement))
+ return TokError("unexpected token in '.end_data_region' directive");
+
+ Lex();
+ getStreamer().EmitDataRegion(MCDR_DataRegionEnd);
+ return false;
+}
+
namespace llvm {
MCAsmParserExtension *createDarwinAsmParser() {
diff --git a/lib/MC/MCStreamer.cpp b/lib/MC/MCStreamer.cpp
index 43e62ff..e363f28 100644
--- a/lib/MC/MCStreamer.cpp
+++ b/lib/MC/MCStreamer.cpp
@@ -20,12 +20,9 @@
#include <cstdlib>
using namespace llvm;
-MCStreamer::MCStreamer(MCContext &Ctx) : Context(Ctx), EmitEHFrame(true),
- EmitDebugFrame(false),
- CurrentW64UnwindInfo(0),
- LastSymbol(0),
- UniqueCodeBeginSuffix(0),
- UniqueDataBeginSuffix(0) {
+MCStreamer::MCStreamer(MCContext &Ctx)
+ : Context(Ctx), EmitEHFrame(true), EmitDebugFrame(false),
+ CurrentW64UnwindInfo(0), LastSymbol(0) {
const MCSection *section = NULL;
SectionStack.push_back(std::make_pair(section, section));
}
@@ -183,85 +180,6 @@
LastSymbol = Symbol;
}
-void MCStreamer::EmitDataRegion() {
- if (RegionIndicator == Data) return;
-
- MCContext &Context = getContext();
- const MCAsmInfo &MAI = Context.getAsmInfo();
- if (!MAI.getSupportsDataRegions()) return;
-
- // Generate a unique symbol name.
- MCSymbol *NewSym = Context.GetOrCreateSymbol(MAI.getDataBeginLabelName() +
- Twine(UniqueDataBeginSuffix++));
- EmitLabel(NewSym);
-
- RegionIndicator = Data;
-}
-
-void MCStreamer::EmitCodeRegion() {
- if (RegionIndicator == Code) return;
-
- MCContext &Context = getContext();
- const MCAsmInfo &MAI = Context.getAsmInfo();
- if (!MAI.getSupportsDataRegions()) return;
-
- // Generate a unique symbol name.
- MCSymbol *NewSym = Context.GetOrCreateSymbol(MAI.getCodeBeginLabelName() +
- Twine(UniqueCodeBeginSuffix++));
- EmitLabel(NewSym);
-
- RegionIndicator = Code;
-}
-
-void MCStreamer::EmitJumpTable8Region() {
- if (RegionIndicator == JumpTable8) return;
-
- MCContext &Context = getContext();
- const MCAsmInfo &MAI = Context.getAsmInfo();
- if (!MAI.getSupportsDataRegions()) return;
-
- // Generate a unique symbol name.
- MCSymbol *NewSym =
- Context.GetOrCreateSymbol(MAI.getJumpTable8BeginLabelName() +
- Twine(UniqueDataBeginSuffix++));
- EmitLabel(NewSym);
-
- RegionIndicator = JumpTable8;
-}
-
-void MCStreamer::EmitJumpTable16Region() {
- if (RegionIndicator == JumpTable16) return;
-
- MCContext &Context = getContext();
- const MCAsmInfo &MAI = Context.getAsmInfo();
- if (!MAI.getSupportsDataRegions()) return;
-
- // Generate a unique symbol name.
- MCSymbol *NewSym =
- Context.GetOrCreateSymbol(MAI.getJumpTable16BeginLabelName() +
- Twine(UniqueDataBeginSuffix++));
- EmitLabel(NewSym);
-
- RegionIndicator = JumpTable16;
-}
-
-
-void MCStreamer::EmitJumpTable32Region() {
- if (RegionIndicator == JumpTable32) return;
-
- MCContext &Context = getContext();
- const MCAsmInfo &MAI = Context.getAsmInfo();
- if (!MAI.getSupportsDataRegions()) return;
-
- // Generate a unique symbol name.
- MCSymbol *NewSym =
- Context.GetOrCreateSymbol(MAI.getJumpTable32BeginLabelName() +
- Twine(UniqueDataBeginSuffix++));
- EmitLabel(NewSym);
-
- RegionIndicator = JumpTable32;
-}
-
void MCStreamer::EmitCompactUnwindEncoding(uint32_t CompactUnwindEncoding) {
EnsureValidFrame();
MCDwarfFrameInfo *CurFrame = getCurrentFrameInfo();
@@ -283,7 +201,6 @@
EmitCFIStartProcImpl(Frame);
FrameInfos.push_back(Frame);
- RegionIndicator = Code;
}
void MCStreamer::EmitCFIStartProcImpl(MCDwarfFrameInfo &Frame) {
diff --git a/lib/MC/MachObjectWriter.cpp b/lib/MC/MachObjectWriter.cpp
index 8e4066c..5820a22 100644
--- a/lib/MC/MachObjectWriter.cpp
+++ b/lib/MC/MachObjectWriter.cpp
@@ -21,6 +21,7 @@
#include "llvm/MC/MCMachOSymbolFlags.h"
#include "llvm/MC/MCValue.h"
#include "llvm/Object/MachOFormat.h"
+#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include <vector>
@@ -351,6 +352,21 @@
Write32(Address);
}
+void MachObjectWriter::WriteLinkeditLoadCommand(uint32_t Type,
+ uint32_t DataOffset,
+ uint32_t DataSize) {
+ uint64_t Start = OS.tell();
+ (void) Start;
+
+ Write32(Type);
+ Write32(macho::LinkeditLoadCommandSize);
+ Write32(DataOffset);
+ Write32(DataSize);
+
+ assert(OS.tell() - Start == macho::LinkeditLoadCommandSize);
+}
+
+
void MachObjectWriter::RecordRelocation(const MCAssembler &Asm,
const MCAsmLayout &Layout,
const MCFragment *Fragment,
@@ -654,6 +670,13 @@
macho::DysymtabLoadCommandSize);
}
+ // Add the data-in-code load command size, if used.
+ unsigned NumDataRegions = Asm.getDataRegions().size();
+ if (NumDataRegions) {
+ ++NumLoadCommands;
+ LoadCommandsSize += macho::LinkeditLoadCommandSize;
+ }
+
// Compute the total size of the section data, as well as its file size and vm
// size.
uint64_t SectionDataStart = (is64Bit() ? macho::Header64Size :
@@ -701,6 +724,15 @@
RelocTableEnd += NumRelocs * macho::RelocationInfoSize;
}
+ // Write the data-in-code load command, if used.
+ uint64_t DataInCodeTableEnd = RelocTableEnd + NumDataRegions * 8;
+ if (NumDataRegions) {
+ uint64_t DataRegionsOffset = RelocTableEnd;
+ uint64_t DataRegionsSize = NumDataRegions * 8;
+ WriteLinkeditLoadCommand(macho::LCT_DataInCode, DataRegionsOffset,
+ DataRegionsSize);
+ }
+
// Write the symbol table load command, if used.
if (NumSymbols) {
unsigned FirstLocalSymbol = 0;
@@ -717,10 +749,10 @@
// If used, the indirect symbols are written after the section data.
if (NumIndirectSymbols)
- IndirectSymbolOffset = RelocTableEnd;
+ IndirectSymbolOffset = DataInCodeTableEnd;
// The symbol table is written after the indirect symbol data.
- uint64_t SymbolTableOffset = RelocTableEnd + IndirectSymbolSize;
+ uint64_t SymbolTableOffset = DataInCodeTableEnd + IndirectSymbolSize;
// The string table is written after symbol table.
uint64_t StringTableOffset =
@@ -760,6 +792,23 @@
}
}
+ // Write out the data-in-code region payload, if there is one.
+ for (MCAssembler::const_data_region_iterator
+ it = Asm.data_region_begin(), ie = Asm.data_region_end();
+ it != ie; ++it) {
+ const DataRegionData *Data = &(*it);
+ uint64_t Start = getSymbolAddress(&Layout.getAssembler().getSymbolData(*Data->Start), Layout);
+ uint64_t End = getSymbolAddress(&Layout.getAssembler().getSymbolData(*Data->End), Layout);
+ DEBUG(dbgs() << "data in code region-- kind: " << Data->Kind
+ << " start: " << Start << "(" << Data->Start->getName() << ")"
+ << " end: " << End << "(" << Data->End->getName() << ")"
+ << " size: " << End - Start
+ << "\n");
+ Write32(Start);
+ Write16(End - Start);
+ Write16(Data->Kind);
+ }
+
// Write the symbol table data, if used.
if (NumSymbols) {
// Write the indirect symbol entries.