Add a function to get the segment name of a section.

On MachO, sections also have segment names. When a tool looking at a .o file
prints a segment name, this is what they mean. In reality, a .o has only one
anonymous, segment.

This patch adds a MachO only function to fetch that segment name. I named it
getSectionFinalSegmentName since the main use for the name seems to be inform
the linker with segment this section should go to.

The patch also changes MachOObjectFile::getSectionName to return just the
section name instead of computing SegmentName,SectionName.

The main difference from the previous patch is that it doesn't use
InMemoryStruct. It is extremely dangerous: if the endians match it returns
a pointer to the file buffer, if not, it returns a pointer to an internal buffer
that is overwritten in the next API call.

We should change all of this code to use
support::detail::packed_endian_specific_integral like ELF, but since these
functions only handle strings, they work with big and little endian machines
as is.

I have tested this by installing ubuntu 12.10 ppc on qemu, that is why it took
so long :-)

llvm-svn: 170838

llvm/include/llvm/Object/MachO.h

@@ -44,6 +44,11 @@ public:
   virtual unsigned getArch() const;
   virtual StringRef getLoadName() const;
 
+  // In a MachO file, sections have a segment name. This is used in the .o
+  // files. They have a single segment, but this field specifies which segment
+  // a section should be put in in the final object.
+  error_code getSectionFinalSegmentName(DataRefImpl Sec, StringRef &Res) const;
+
   MachOObject *getObject() { return MachOObj.get(); }
 
   static inline bool classof(const Binary *v) {

llvm/lib/Object/MachOObjectFile.cpp

@@ -473,28 +473,55 @@ static bool is64BitLoadCommand(const MachOObject *MachOObj, DataRefImpl DRI) {
   return false;
 }
 
+static StringRef parseSegmentOrSectionName(const char *P) {
+  if (P[15] == 0)
+    // Null terminated.
+    return P;
+  // Not null terminated, so this is a 16 char string.
+  return StringRef(P, 16);
+}
+
 error_code MachOObjectFile::getSectionName(DataRefImpl DRI,
                                            StringRef &Result) const {
-  // FIXME: thread safety.
-  static char result[34];
   if (is64BitLoadCommand(MachOObj.get(), DRI)) {
     LoadCommandInfo LCI = MachOObj->getLoadCommandInfo(DRI.d.a);
-    InMemoryStruct<macho::Section64> Sect;
-    MachOObj->ReadSection64(LCI, DRI.d.b, Sect);
-
-    strcpy(result, Sect->SegmentName);
-    strcat(result, ",");
-    strcat(result, Sect->Name);
+    unsigned SectionOffset = LCI.Offset + sizeof(macho::Segment64LoadCommand) +
+      DRI.d.b * sizeof(macho::Section64);
+    StringRef Data = MachOObj->getData(SectionOffset, sizeof(macho::Section64));
+    const macho::Section64 *sec =
+      reinterpret_cast<const macho::Section64*>(Data.data());
+    Result = parseSegmentOrSectionName(sec->Name);
   } else {
     LoadCommandInfo LCI = MachOObj->getLoadCommandInfo(DRI.d.a);
-    InMemoryStruct<macho::Section> Sect;
-    MachOObj->ReadSection(LCI, DRI.d.b, Sect);
-
-    strcpy(result, Sect->SegmentName);
-    strcat(result, ",");
-    strcat(result, Sect->Name);
+    unsigned SectionOffset = LCI.Offset + sizeof(macho::SegmentLoadCommand) +
+      DRI.d.b * sizeof(macho::Section);
+    StringRef Data = MachOObj->getData(SectionOffset, sizeof(macho::Section));
+    const macho::Section *sec =
+      reinterpret_cast<const macho::Section*>(Data.data());
+    Result = parseSegmentOrSectionName(sec->Name);
+  }
+  return object_error::success;
+}
+
+error_code MachOObjectFile::getSectionFinalSegmentName(DataRefImpl Sec,
+                                                       StringRef &Res) const {
+  if (is64BitLoadCommand(MachOObj.get(), Sec)) {
+    LoadCommandInfo LCI = MachOObj->getLoadCommandInfo(Sec.d.a);
+    unsigned SectionOffset = LCI.Offset + sizeof(macho::Segment64LoadCommand) +
+      Sec.d.b * sizeof(macho::Section64);
+    StringRef Data = MachOObj->getData(SectionOffset, sizeof(macho::Section64));
+    const macho::Section64 *sec =
+      reinterpret_cast<const macho::Section64*>(Data.data());
+    Res = parseSegmentOrSectionName(sec->SegmentName);
+  } else {
+    LoadCommandInfo LCI = MachOObj->getLoadCommandInfo(Sec.d.a);
+    unsigned SectionOffset = LCI.Offset + sizeof(macho::SegmentLoadCommand) +
+      Sec.d.b * sizeof(macho::Section);
+    StringRef Data = MachOObj->getData(SectionOffset, sizeof(macho::Section));
+    const macho::Section *sec =
+      reinterpret_cast<const macho::Section*>(Data.data());
+    Res = parseSegmentOrSectionName(sec->SegmentName);
   }
-  Result = StringRef(result);
   return object_error::success;
 }
 

llvm/tools/llvm-objdump/MachODump.cpp

@@ -334,9 +334,15 @@ void llvm::DisassembleInputMachO(StringRef Filename) {
   for (unsigned SectIdx = 0; SectIdx != Sections.size(); SectIdx++) {
     StringRef SectName;
     if (Sections[SectIdx].getName(SectName) ||
-        SectName.compare("__TEXT,__text"))
+        SectName != "__text")
       continue; // Skip non-text sections
 
+    StringRef SegmentName;
+    DataRefImpl DR = Sections[SectIdx].getRawDataRefImpl();
+    if (MachOOF->getSectionFinalSegmentName(DR, SegmentName) ||
+        SegmentName != "__TEXT")
+      continue;
+
     // Insert the functions from the function starts segment into our map.
     uint64_t VMAddr;
     Sections[SectIdx].getAddress(VMAddr);

llvm/tools/llvm-objdump/llvm-objdump.cpp

@@ -28,6 +28,7 @@
 #include "llvm/MC/MCSubtargetInfo.h"
 #include "llvm/Object/Archive.h"
 #include "llvm/Object/COFF.h"
+#include "llvm/Object/MachO.h"
 #include "llvm/Object/ObjectFile.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/CommandLine.h"
@@ -72,9 +73,9 @@ static cl::opt<bool>
 SymbolTable("t", cl::desc("Display the symbol table"));
 
 static cl::opt<bool>
-MachO("macho", cl::desc("Use MachO specific object file parser"));
+MachOOpt("macho", cl::desc("Use MachO specific object file parser"));
 static cl::alias
-MachOm("m", cl::desc("Alias for --macho"), cl::aliasopt(MachO));
+MachOm("m", cl::desc("Alias for --macho"), cl::aliasopt(MachOOpt));
 
 cl::opt<std::string>
 llvm::TripleName("triple", cl::desc("Target triple to disassemble for, "
@@ -241,9 +242,18 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) {
     // Sort relocations by address.
     std::sort(Rels.begin(), Rels.end(), RelocAddressLess);
 
+    StringRef SegmentName = "";
+    if (const MachOObjectFile *MachO = dyn_cast<const MachOObjectFile>(Obj)) {
+      DataRefImpl DR = i->getRawDataRefImpl();
+      if (error(MachO->getSectionFinalSegmentName(DR, SegmentName)))
+        break;
+    }
     StringRef name;
     if (error(i->getName(name))) break;
-    outs() << "Disassembly of section " << name << ':';
+    outs() << "Disassembly of section ";
+    if (!SegmentName.empty())
+      outs() << SegmentName << ",";
+    outs() << name << ':';
 
     // If the section has no symbols just insert a dummy one and disassemble
     // the whole section.
@@ -567,6 +577,13 @@ static void PrintSymbolTable(const ObjectFile *o) {
       else if (Section == o->end_sections())
         outs() << "*UND*";
       else {
+        if (const MachOObjectFile *MachO = dyn_cast<const MachOObjectFile>(o)) {
+          StringRef SegmentName;
+          DataRefImpl DR = Section->getRawDataRefImpl();
+          if (error(MachO->getSectionFinalSegmentName(DR, SegmentName)))
+            SegmentName = "";
+          outs() << SegmentName << ",";
+        }
         StringRef SectionName;
         if (error(Section->getName(SectionName)))
           SectionName = "";
@@ -640,7 +657,7 @@ static void DumpInput(StringRef file) {
     return;
   }
 
-  if (MachO && Disassemble) {
+  if (MachOOpt && Disassemble) {
     DisassembleInputMachO(file);
     return;
   }