[llvm] r188884 - MC CFG: Add "dynamic disassembly" support to MCObjectDisassembler.

[Ahmed Bougacha]

Author: ab
Date: Wed Aug 21 02:28:37 2013
New Revision: 188884

URL: http://llvm.org/viewvc/llvm-project?rev=188884&view=rev
Log:
MC CFG: Add "dynamic disassembly" support to MCObjectDisassembler.

It can now disassemble code in situations where the effective load
address is different than the load address declared in the object file.
This happens for PIC, hence "dynamic".

Modified:
    llvm/trunk/include/llvm/MC/MCObjectDisassembler.h
    llvm/trunk/lib/MC/MCObjectDisassembler.cpp

Modified: llvm/trunk/include/llvm/MC/MCObjectDisassembler.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/MC/MCObjectDisassembler.h?rev=188884&r1=188883&r2=188884&view=diff
==============================================================================
--- llvm/trunk/include/llvm/MC/MCObjectDisassembler.h (original)
+++ llvm/trunk/include/llvm/MC/MCObjectDisassembler.h Wed Aug 21 02:28:37 2013
@@ -65,6 +65,22 @@ public:
   virtual ArrayRef<uint64_t> getStaticExitFunctions();
   /// @}
 
+  /// \name Translation between effective and objectfile load address.
+  /// @{
+  /// \brief Compute the effective load address, from an objectfile virtual
+  /// address. This is implemented in a format-specific way, to take into
+  /// account things like PIE/ASLR when doing dynamic disassembly.
+  /// For example, on Mach-O this would be done by adding the VM addr slide,
+  /// on glibc ELF by keeping a map between segment load addresses, filled
+  /// using dl_iterate_phdr, etc..
+  /// In most static situations and in the default impl., this returns \p Addr.
+  virtual uint64_t getEffectiveLoadAddr(uint64_t Addr);
+
+  /// \brief Compute the original load address, as specified in the objectfile.
+  /// This is the inverse of getEffectiveLoadAddr.
+  virtual uint64_t getOriginalLoadAddr(uint64_t EffectiveAddr);
+  /// @}
+
 protected:
   const object::ObjectFile &Obj;
   const MCDisassembler &Dis;

Modified: llvm/trunk/lib/MC/MCObjectDisassembler.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/MC/MCObjectDisassembler.cpp?rev=188884&r1=188883&r2=188884&view=diff
==============================================================================
--- llvm/trunk/lib/MC/MCObjectDisassembler.cpp (original)
+++ llvm/trunk/lib/MC/MCObjectDisassembler.cpp Wed Aug 21 02:28:37 2013
@@ -44,7 +44,7 @@ uint64_t MCObjectDisassembler::getEntryp
     if (Name == "main" || Name == "_main") {
       uint64_t Entrypoint;
       SI->getAddress(Entrypoint);
-      return Entrypoint;
+      return getEffectiveLoadAddr(Entrypoint);
     }
   }
   return 0;
@@ -58,6 +58,14 @@ ArrayRef<uint64_t> MCObjectDisassembler:
   return ArrayRef<uint64_t>();
 }
 
+uint64_t MCObjectDisassembler::getEffectiveLoadAddr(uint64_t Addr) {
+  return Addr;
+}
+
+uint64_t MCObjectDisassembler::getOriginalLoadAddr(uint64_t Addr) {
+  return Addr;
+}
+
 MCModule *MCObjectDisassembler::buildEmptyModule() {
   MCModule *Module = new MCModule;
   Module->Entrypoint = getEntrypoint();
@@ -90,6 +98,7 @@ void MCObjectDisassembler::buildSectionA
     uint64_t SecSize; SI->getSize(SecSize);
     if (StartAddr == UnknownAddressOrSize || SecSize == UnknownAddressOrSize)
       continue;
+    StartAddr = getEffectiveLoadAddr(StartAddr);
 
     StringRef Contents; SI->getContents(Contents);
     StringRefMemoryObject memoryObject(Contents, StartAddr);
@@ -170,6 +179,7 @@ void MCObjectDisassembler::buildCFG(MCMo
     if (SymType == SymbolRef::ST_Function) {
       uint64_t SymAddr;
       SI->getAddress(SymAddr);
+      SymAddr = getEffectiveLoadAddr(SymAddr);
       Calls.insert(SymAddr);
       Splits.insert(SymAddr);
     }