4 files changed, 400 insertions, 10 deletions

diff --git a/contrib/llvm/lib/ExecutionEngine/MCJIT/Intercept.cpp b/contrib/llvm/lib/ExecutionEngine/MCJIT/Intercept.cpp
new file mode 100644
index 0000000..e431c84
--- /dev/null
+++ b/contrib/llvm/lib/ExecutionEngine/MCJIT/Intercept.cpp
@@ -0,0 +1,161 @@
+//===-- Intercept.cpp - System function interception routines -------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// If a function call occurs to an external function, the JIT is designed to use
+// the dynamic loader interface to find a function to call.  This is useful for
+// calling system calls and library functions that are not available in LLVM.
+// Some system calls, however, need to be handled specially.  For this reason,
+// we intercept some of them here and use our own stubs to handle them.
+//
+//===----------------------------------------------------------------------===//
+
+#include "MCJIT.h"
+#include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/DynamicLibrary.h"
+#include "llvm/Config/config.h"
+using namespace llvm;
+
+// AtExitHandlers - List of functions to call when the program exits,
+// registered with the atexit() library function.
+static std::vector<void (*)()> AtExitHandlers;
+
+/// runAtExitHandlers - Run any functions registered by the program's
+/// calls to atexit(3), which we intercept and store in
+/// AtExitHandlers.
+///
+static void runAtExitHandlers() {
+  while (!AtExitHandlers.empty()) {
+    void (*Fn)() = AtExitHandlers.back();
+    AtExitHandlers.pop_back();
+    Fn();
+  }
+}
+
+//===----------------------------------------------------------------------===//
+// Function stubs that are invoked instead of certain library calls
+//===----------------------------------------------------------------------===//
+
+// Force the following functions to be linked in to anything that uses the
+// JIT. This is a hack designed to work around the all-too-clever Glibc
+// strategy of making these functions work differently when inlined vs. when
+// not inlined, and hiding their real definitions in a separate archive file
+// that the dynamic linker can't see. For more info, search for
+// 'libc_nonshared.a' on Google, or read http://llvm.org/PR274.
+#if defined(__linux__)
+#if defined(HAVE_SYS_STAT_H)
+#include <sys/stat.h>
+#endif
+#include <fcntl.h>
+/* stat functions are redirecting to __xstat with a version number.  On x86-64
+ * linking with libc_nonshared.a and -Wl,--export-dynamic doesn't make 'stat'
+ * available as an exported symbol, so we have to add it explicitly.
+ */
+namespace {
+class StatSymbols {
+public:
+  StatSymbols() {
+    sys::DynamicLibrary::AddSymbol("stat", (void*)(intptr_t)stat);
+    sys::DynamicLibrary::AddSymbol("fstat", (void*)(intptr_t)fstat);
+    sys::DynamicLibrary::AddSymbol("lstat", (void*)(intptr_t)lstat);
+    sys::DynamicLibrary::AddSymbol("stat64", (void*)(intptr_t)stat64);
+    sys::DynamicLibrary::AddSymbol("\x1stat64", (void*)(intptr_t)stat64);
+    sys::DynamicLibrary::AddSymbol("\x1open64", (void*)(intptr_t)open64);
+    sys::DynamicLibrary::AddSymbol("\x1lseek64", (void*)(intptr_t)lseek64);
+    sys::DynamicLibrary::AddSymbol("fstat64", (void*)(intptr_t)fstat64);
+    sys::DynamicLibrary::AddSymbol("lstat64", (void*)(intptr_t)lstat64);
+    sys::DynamicLibrary::AddSymbol("atexit", (void*)(intptr_t)atexit);
+    sys::DynamicLibrary::AddSymbol("mknod", (void*)(intptr_t)mknod);
+  }
+};
+}
+static StatSymbols initStatSymbols;
+#endif // __linux__
+
+// jit_exit - Used to intercept the "exit" library call.
+static void jit_exit(int Status) {
+  runAtExitHandlers();   // Run atexit handlers...
+  exit(Status);
+}
+
+// jit_atexit - Used to intercept the "atexit" library call.
+static int jit_atexit(void (*Fn)()) {
+  AtExitHandlers.push_back(Fn);    // Take note of atexit handler...
+  return 0;  // Always successful
+}
+
+static int jit_noop() {
+  return 0;
+}
+
+//===----------------------------------------------------------------------===//
+//
+/// getPointerToNamedFunction - This method returns the address of the specified
+/// function by using the dynamic loader interface.  As such it is only useful
+/// for resolving library symbols, not code generated symbols.
+///
+void *MCJIT::getPointerToNamedFunction(const std::string &Name,
+                                       bool AbortOnFailure) {
+  if (!isSymbolSearchingDisabled()) {
+    // Check to see if this is one of the functions we want to intercept.  Note,
+    // we cast to intptr_t here to silence a -pedantic warning that complains
+    // about casting a function pointer to a normal pointer.
+    if (Name == "exit") return (void*)(intptr_t)&jit_exit;
+    if (Name == "atexit") return (void*)(intptr_t)&jit_atexit;
+
+    // We should not invoke parent's ctors/dtors from generated main()!
+    // On Mingw and Cygwin, the symbol __main is resolved to
+    // callee's(eg. tools/lli) one, to invoke wrong duplicated ctors
+    // (and register wrong callee's dtors with atexit(3)).
+    // We expect ExecutionEngine::runStaticConstructorsDestructors()
+    // is called before ExecutionEngine::runFunctionAsMain() is called.
+    if (Name == "__main") return (void*)(intptr_t)&jit_noop;
+
+    const char *NameStr = Name.c_str();
+    // If this is an asm specifier, skip the sentinal.
+    if (NameStr[0] == 1) ++NameStr;
+
+    // If it's an external function, look it up in the process image...
+    void *Ptr = sys::DynamicLibrary::SearchForAddressOfSymbol(NameStr);
+    if (Ptr) return Ptr;
+
+    // If it wasn't found and if it starts with an underscore ('_') character,
+    // and has an asm specifier, try again without the underscore.
+    if (Name[0] == 1 && NameStr[0] == '_') {
+      Ptr = sys::DynamicLibrary::SearchForAddressOfSymbol(NameStr+1);
+      if (Ptr) return Ptr;
+    }
+
+    // Darwin/PPC adds $LDBLStub suffixes to various symbols like printf.  These
+    // are references to hidden visibility symbols that dlsym cannot resolve.
+    // If we have one of these, strip off $LDBLStub and try again.
+#if defined(__APPLE__) && defined(__ppc__)
+    if (Name.size() > 9 && Name[Name.size()-9] == '$' &&
+        memcmp(&Name[Name.size()-8], "LDBLStub", 8) == 0) {
+      // First try turning $LDBLStub into $LDBL128. If that fails, strip it off.
+      // This mirrors logic in libSystemStubs.a.
+      std::string Prefix = std::string(Name.begin(), Name.end()-9);
+      if (void *Ptr = getPointerToNamedFunction(Prefix+"$LDBL128", false))
+        return Ptr;
+      if (void *Ptr = getPointerToNamedFunction(Prefix, false))
+        return Ptr;
+    }
+#endif
+  }
+
+  /// If a LazyFunctionCreator is installed, use it to get/create the function.
+  if (LazyFunctionCreator)
+    if (void *RP = LazyFunctionCreator(Name))
+      return RP;
+
+  if (AbortOnFailure) {
+    report_fatal_error("Program used external function '"+Name+
+                      "' which could not be resolved!");
+  }
+  return 0;
+}
diff --git a/contrib/llvm/lib/ExecutionEngine/MCJIT/MCJIT.cpp b/contrib/llvm/lib/ExecutionEngine/MCJIT/MCJIT.cpp
index f1e9dab..3d4ee36 100644
--- a/contrib/llvm/lib/ExecutionEngine/MCJIT/MCJIT.cpp
+++ b/contrib/llvm/lib/ExecutionEngine/MCJIT/MCJIT.cpp
@@ -1,4 +1,4 @@
-//===-- JIT.cpp - MC-based Just-in-Time Compiler --------------------------===//
+//===-- MCJIT.cpp - MC-based Just-in-Time Compiler ------------------------===//
 //
 //                     The LLVM Compiler Infrastructure
 //
@@ -8,10 +8,17 @@
 //===----------------------------------------------------------------------===//
 
 #include "MCJIT.h"
+#include "MCJITMemoryManager.h"
+#include "llvm/DerivedTypes.h"
+#include "llvm/Function.h"
 #include "llvm/ExecutionEngine/GenericValue.h"
 #include "llvm/ExecutionEngine/MCJIT.h"
+#include "llvm/ExecutionEngine/JITMemoryManager.h"
+#include "llvm/MC/MCAsmInfo.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/DynamicLibrary.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Target/TargetData.h"
 
 using namespace llvm;
 
@@ -51,20 +58,47 @@ ExecutionEngine *MCJIT::createJIT(Module *M,
 
   // If the target supports JIT code generation, create the JIT.
   if (TargetJITInfo *TJ = TM->getJITInfo())
-    return new MCJIT(M, *TM, *TJ, JMM, OptLevel, GVsWithCode);
+    return new MCJIT(M, TM, *TJ, new MCJITMemoryManager(JMM), OptLevel,
+                     GVsWithCode);
 
   if (ErrorStr)
     *ErrorStr = "target does not support JIT code generation";
   return 0;
 }
 
-MCJIT::MCJIT(Module *M, TargetMachine &tm, TargetJITInfo &tji,
-             JITMemoryManager *JMM, CodeGenOpt::Level OptLevel,
+MCJIT::MCJIT(Module *m, TargetMachine *tm, TargetJITInfo &tji,
+             RTDyldMemoryManager *MM, CodeGenOpt::Level OptLevel,
              bool AllocateGVsWithCode)
-  : ExecutionEngine(M) {
+  : ExecutionEngine(m), TM(tm), MemMgr(MM), M(m), OS(Buffer), Dyld(MM) {
+
+  PM.add(new TargetData(*TM->getTargetData()));
+
+  // Turn the machine code intermediate representation into bytes in memory
+  // that may be executed.
+  if (TM->addPassesToEmitMC(PM, Ctx, OS, CodeGenOpt::Default, false)) {
+    report_fatal_error("Target does not support MC emission!");
+  }
+
+  // Initialize passes.
+  // FIXME: When we support multiple modules, we'll want to move the code
+  // gen and finalization out of the constructor here and do it more
+  // on-demand as part of getPointerToFunction().
+  PM.run(*M);
+  // Flush the output buffer so the SmallVector gets its data.
+  OS.flush();
+
+  // Load the object into the dynamic linker.
+  // FIXME: It would be nice to avoid making yet another copy.
+  MemoryBuffer *MB = MemoryBuffer::getMemBufferCopy(StringRef(Buffer.data(),
+                                                              Buffer.size()));
+  if (Dyld.loadObject(MB))
+    report_fatal_error(Dyld.getErrorString());
+  // Resolve any relocations.
+  Dyld.resolveRelocations();
 }
 
 MCJIT::~MCJIT() {
+  delete MemMgr;
 }
 
 void *MCJIT::getPointerToBasicBlock(BasicBlock *BB) {
@@ -73,8 +107,15 @@ void *MCJIT::getPointerToBasicBlock(BasicBlock *BB) {
 }
 
 void *MCJIT::getPointerToFunction(Function *F) {
-  report_fatal_error("not yet implemented");
-  return 0;
+  if (F->isDeclaration() || F->hasAvailableExternallyLinkage()) {
+    bool AbortOnFailure = !F->hasExternalWeakLinkage();
+    void *Addr = getPointerToNamedFunction(F->getName(), AbortOnFailure);
+    addGlobalMapping(F, Addr);
+    return Addr;
+  }
+
+  Twine Name = TM->getMCAsmInfo()->getGlobalPrefix() + F->getName();
+  return (void*)Dyld.getSymbolAddress(Name.str());
 }
 
 void *MCJIT::recompileAndRelinkFunction(Function *F) {
@@ -87,6 +128,102 @@ void MCJIT::freeMachineCodeForFunction(Function *F) {
 
 GenericValue MCJIT::runFunction(Function *F,
                                 const std::vector<GenericValue> &ArgValues) {
-  report_fatal_error("not yet implemented");
+  assert(F && "Function *F was null at entry to run()");
+
+  void *FPtr = getPointerToFunction(F);
+  assert(FPtr && "Pointer to fn's code was null after getPointerToFunction");
+  const FunctionType *FTy = F->getFunctionType();
+  const Type *RetTy = FTy->getReturnType();
+
+  assert((FTy->getNumParams() == ArgValues.size() ||
+          (FTy->isVarArg() && FTy->getNumParams() <= ArgValues.size())) &&
+         "Wrong number of arguments passed into function!");
+  assert(FTy->getNumParams() == ArgValues.size() &&
+         "This doesn't support passing arguments through varargs (yet)!");
+
+  // Handle some common cases first.  These cases correspond to common `main'
+  // prototypes.
+  if (RetTy->isIntegerTy(32) || RetTy->isVoidTy()) {
+    switch (ArgValues.size()) {
+    case 3:
+      if (FTy->getParamType(0)->isIntegerTy(32) &&
+          FTy->getParamType(1)->isPointerTy() &&
+          FTy->getParamType(2)->isPointerTy()) {
+        int (*PF)(int, char **, const char **) =
+          (int(*)(int, char **, const char **))(intptr_t)FPtr;
+
+        // Call the function.
+        GenericValue rv;
+        rv.IntVal = APInt(32, PF(ArgValues[0].IntVal.getZExtValue(),
+                                 (char **)GVTOP(ArgValues[1]),
+                                 (const char **)GVTOP(ArgValues[2])));
+        return rv;
+      }
+      break;
+    case 2:
+      if (FTy->getParamType(0)->isIntegerTy(32) &&
+          FTy->getParamType(1)->isPointerTy()) {
+        int (*PF)(int, char **) = (int(*)(int, char **))(intptr_t)FPtr;
+
+        // Call the function.
+        GenericValue rv;
+        rv.IntVal = APInt(32, PF(ArgValues[0].IntVal.getZExtValue(),
+                                 (char **)GVTOP(ArgValues[1])));
+        return rv;
+      }
+      break;
+    case 1:
+      if (FTy->getNumParams() == 1 &&
+          FTy->getParamType(0)->isIntegerTy(32)) {
+        GenericValue rv;
+        int (*PF)(int) = (int(*)(int))(intptr_t)FPtr;
+        rv.IntVal = APInt(32, PF(ArgValues[0].IntVal.getZExtValue()));
+        return rv;
+      }
+      break;
+    }
+  }
+
+  // Handle cases where no arguments are passed first.
+  if (ArgValues.empty()) {
+    GenericValue rv;
+    switch (RetTy->getTypeID()) {
+    default: llvm_unreachable("Unknown return type for function call!");
+    case Type::IntegerTyID: {
+      unsigned BitWidth = cast<IntegerType>(RetTy)->getBitWidth();
+      if (BitWidth == 1)
+        rv.IntVal = APInt(BitWidth, ((bool(*)())(intptr_t)FPtr)());
+      else if (BitWidth <= 8)
+        rv.IntVal = APInt(BitWidth, ((char(*)())(intptr_t)FPtr)());
+      else if (BitWidth <= 16)
+        rv.IntVal = APInt(BitWidth, ((short(*)())(intptr_t)FPtr)());
+      else if (BitWidth <= 32)
+        rv.IntVal = APInt(BitWidth, ((int(*)())(intptr_t)FPtr)());
+      else if (BitWidth <= 64)
+        rv.IntVal = APInt(BitWidth, ((int64_t(*)())(intptr_t)FPtr)());
+      else
+        llvm_unreachable("Integer types > 64 bits not supported");
+      return rv;
+    }
+    case Type::VoidTyID:
+      rv.IntVal = APInt(32, ((int(*)())(intptr_t)FPtr)());
+      return rv;
+    case Type::FloatTyID:
+      rv.FloatVal = ((float(*)())(intptr_t)FPtr)();
+      return rv;
+    case Type::DoubleTyID:
+      rv.DoubleVal = ((double(*)())(intptr_t)FPtr)();
+      return rv;
+    case Type::X86_FP80TyID:
+    case Type::FP128TyID:
+    case Type::PPC_FP128TyID:
+      llvm_unreachable("long double not supported yet");
+      return rv;
+    case Type::PointerTyID:
+      return PTOGV(((void*(*)())(intptr_t)FPtr)());
+    }
+  }
+
+  assert("Full-featured argument passing not supported yet!");
   return GenericValue();
 }
diff --git a/contrib/llvm/lib/ExecutionEngine/MCJIT/MCJIT.h b/contrib/llvm/lib/ExecutionEngine/MCJIT/MCJIT.h
index cd1f989..1b50766 100644
--- a/contrib/llvm/lib/ExecutionEngine/MCJIT/MCJIT.h
+++ b/contrib/llvm/lib/ExecutionEngine/MCJIT/MCJIT.h
@@ -10,14 +10,37 @@
 #ifndef LLVM_LIB_EXECUTIONENGINE_MCJIT_H
 #define LLVM_LIB_EXECUTIONENGINE_MCJIT_H
 
+#include "llvm/PassManager.h"
 #include "llvm/ExecutionEngine/ExecutionEngine.h"
+#include "llvm/ExecutionEngine/RuntimeDyld.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/Support/raw_ostream.h"
 
 namespace llvm {
 
+// FIXME: This makes all kinds of horrible assumptions for the time being,
+// like only having one module, not needing to worry about multi-threading,
+// blah blah. Purely in get-it-up-and-limping mode for now.
+
 class MCJIT : public ExecutionEngine {
-  MCJIT(Module *M, TargetMachine &tm, TargetJITInfo &tji,
-        JITMemoryManager *JMM, CodeGenOpt::Level OptLevel,
+  MCJIT(Module *M, TargetMachine *tm, TargetJITInfo &tji,
+        RTDyldMemoryManager *MemMgr, CodeGenOpt::Level OptLevel,
         bool AllocateGVsWithCode);
+
+  TargetMachine *TM;
+  MCContext *Ctx;
+  RTDyldMemoryManager *MemMgr;
+
+  // FIXME: These may need moved to a separate 'jitstate' member like the
+  // non-MC JIT does for multithreading and such. Just keep them here for now.
+  PassManager PM;
+  Module *M;
+  // FIXME: This really doesn't belong here.
+  SmallVector<char, 4096> Buffer; // Working buffer into which we JIT.
+  raw_svector_ostream OS;
+
+  RuntimeDyld Dyld;
+
 public:
   ~MCJIT();
 
@@ -35,6 +58,16 @@ public:
   virtual GenericValue runFunction(Function *F,
                                    const std::vector<GenericValue> &ArgValues);
 
+  /// getPointerToNamedFunction - This method returns the address of the
+  /// specified function by using the dlsym function call.  As such it is only
+  /// useful for resolving library symbols, not code generated symbols.
+  ///
+  /// If AbortOnFailure is false and no function with the given name is
+  /// found, this function silently returns a null pointer. Otherwise,
+  /// it prints a message to stderr and aborts.
+  ///
+  void *getPointerToNamedFunction(const std::string &Name,
+                                  bool AbortOnFailure = true);
   /// @}
   /// @name (Private) Registration Interfaces
   /// @{
diff --git a/contrib/llvm/lib/ExecutionEngine/MCJIT/MCJITMemoryManager.h b/contrib/llvm/lib/ExecutionEngine/MCJIT/MCJITMemoryManager.h
new file mode 100644
index 0000000..e3c6fda
--- /dev/null
+++ b/contrib/llvm/lib/ExecutionEngine/MCJIT/MCJITMemoryManager.h
@@ -0,0 +1,59 @@
+//===-- MCJITMemoryManager.h - Definition for the Memory Manager ---C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIB_EXECUTIONENGINE_MCJITMEMORYMANAGER_H
+#define LLVM_LIB_EXECUTIONENGINE_MCJITMEMORYMANAGER_H
+
+#include "llvm/Module.h"
+#include "llvm/ExecutionEngine/JITMemoryManager.h"
+#include "llvm/ExecutionEngine/RuntimeDyld.h"
+#include <assert.h>
+
+namespace llvm {
+
+// The MCJIT memory manager is a layer between the standard JITMemoryManager
+// and the RuntimeDyld interface that maps objects, by name, onto their
+// matching LLVM IR counterparts in the module(s) being compiled.
+class MCJITMemoryManager : public RTDyldMemoryManager {
+  JITMemoryManager *JMM;
+
+  // FIXME: Multiple modules.
+  Module *M;
+public:
+  MCJITMemoryManager(JITMemoryManager *jmm) : JMM(jmm) {}
+
+  // Allocate ActualSize bytes, or more, for the named function. Return
+  // a pointer to the allocated memory and update Size to reflect how much
+  // memory was acutally allocated.
+  uint8_t *startFunctionBody(const char *Name, uintptr_t &Size) {
+    // FIXME: This should really reference the MCAsmInfo to get the global
+    //        prefix.
+    if (Name[0] == '_') ++Name;
+    Function *F = M->getFunction(Name);
+    assert(F && "No matching function in JIT IR Module!");
+    return JMM->startFunctionBody(F, Size);
+  }
+
+  // Mark the end of the function, including how much of the allocated
+  // memory was actually used.
+  void endFunctionBody(const char *Name, uint8_t *FunctionStart,
+                       uint8_t *FunctionEnd) {
+    // FIXME: This should really reference the MCAsmInfo to get the global
+    //        prefix.
+    if (Name[0] == '_') ++Name;
+    Function *F = M->getFunction(Name);
+    assert(F && "No matching function in JIT IR Module!");
+    JMM->endFunctionBody(F, FunctionStart, FunctionEnd);
+  }
+
+};
+
+} // End llvm namespace
+
+#endif