[LibFuzzer] Reimplement how the optional user functions are called.

The motivation for this change is to fix linking issues on OSX.
However this only partially fixes linking issues (the uninstrumented
tests and a few others  won't succesfully link yet).

This change introduces a struct of function pointers
(``fuzzer::ExternalFuntions``) which when initialised will point to the
optional functions if they are available.  Currently these
``LLVMFuzzerInitialize`` and ``LLVMFuzzerCustomMutator`` functions.

Two implementations of ``fuzzer::ExternalFunctions`` constructor are
provided one for Linux and one for OSX.

The OSX implementation uses ``dlsym()`` because the prior implementation
using weak symbols does not work unless the additional flags are passed
to the linker.

The Linux implementation continues to use weak symbols because the
``dlsym()`` approach does not work unless additional flags are passed
to the linker.

Differential Revision: http://reviews.llvm.org/D20741

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@271491 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Fuzzer/CMakeLists.txt

@@ -12,6 +12,8 @@ if( LLVM_USE_SANITIZE_COVERAGE )
     FuzzerCrossOver.cpp
     FuzzerTraceState.cpp
     FuzzerDriver.cpp
+    FuzzerExtFunctionsDlsym.cpp
+    FuzzerExtFunctionsWeak.cpp
     FuzzerIO.cpp
     FuzzerLoop.cpp
     FuzzerMutate.cpp

lib/Fuzzer/FuzzerDriver.cpp

@@ -266,9 +266,13 @@ static bool AllInputsAreFiles() {
   return true;
 }
 
-static int FuzzerDriver(const std::vector<std::string> &Args,
-                        UserCallback Callback) {
+int FuzzerDriver(int *argc, char ***argv, UserCallback Callback) {
   using namespace fuzzer;
+  assert(argc && argv && "Argument pointers cannot be nullptr");
+  fuzzer::ExternalFunctions EF;
+  if (EF.LLVMFuzzerInitialize)
+    EF.LLVMFuzzerInitialize(argc, argv);
+  const std::vector<std::string> Args(*argv, *argv + *argc);
   assert(!Args.empty());
   ProgName = new std::string(Args[0]);
   ParseFlags(Args);
@@ -417,10 +421,4 @@ static int FuzzerDriver(const std::vector<std::string> &Args,
 
   exit(0);  // Don't let F destroy itself.
 }
-
-int FuzzerDriver(int argc, char **argv, UserCallback Callback) {
-  std::vector<std::string> Args(argv, argv + argc);
-  return FuzzerDriver(Args, Callback);
-}
-
 }  // namespace fuzzer

lib/Fuzzer/FuzzerExtFunctions.def

@@ -0,0 +1,23 @@
+//===- FuzzerExtFunctions.def - External functions --------------*- C++ -* ===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+// This defines the external function pointers that
+// ``fuzzer::ExternalFunctions`` should contain and try to initialize.  The
+// EXT_FUNC macro must be defined at the point of inclusion. The signature of
+// the macro is:
+//
+// EXT_FUNC(<name>, <return_type>, <function_signature>, <warn_if_missing>)
+//===----------------------------------------------------------------------===//
+
+// Optional user functions
+EXT_FUNC(LLVMFuzzerInitialize, int, (int *argc, char ***argv), false);
+EXT_FUNC(LLVMFuzzerCustomMutator, size_t,
+         (uint8_t * Data, size_t Size, size_t MaxSize, unsigned int Seed),
+         false);
+
+// TODO: Sanitizer functions

lib/Fuzzer/FuzzerExtFunctions.h

@@ -0,0 +1,32 @@
+//===- FuzzerExtFunctions.h - Interface to external functions ---*- C++ -* ===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+// Defines an interface to (possibly optional) functions.
+//===----------------------------------------------------------------------===//
+#ifndef LLVM_FUZZER_EXT_FUNCTIONS_H
+#define LLVM_FUZZER_EXT_FUNCTIONS_H
+
+#include <stddef.h>
+#include <stdint.h>
+
+namespace fuzzer {
+
+struct ExternalFunctions {
+  // Initialize function pointers. Functions that are not available
+  // will be set to nullptr.
+  ExternalFunctions();
+
+#define EXT_FUNC(NAME, RETURN_TYPE, FUNC_SIG, WARN)                            \
+  RETURN_TYPE(*NAME) FUNC_SIG = nullptr
+
+#include "FuzzerExtFunctions.def"
+
+#undef EXT_FUNC
+};
+} // namespace fuzzer
+#endif

lib/Fuzzer/FuzzerExtFunctionsDlsym.cpp

@@ -0,0 +1,49 @@
+//===- FuzzerExtFunctionsDlsym.cpp - Interface to external functions ------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+// Implementation for operating systems that support dlsym(). We only use it on
+// Apple platforms for now. We don't use this approach on Linux because it
+// requires that clients of LibFuzzer pass ``--export-dynamic`` to the linker.
+// That is a complication we don't wish to expose to clients right now.
+//===----------------------------------------------------------------------===//
+#include "FuzzerInternal.h"
+#if LIBFUZZER_APPLE
+
+#include "FuzzerExtFunctions.h"
+#include <dlfcn.h>
+
+using namespace fuzzer;
+
+template <typename T>
+static T GetFnPtr(const char *FnName, bool WarnIfMissing) {
+  dlerror(); // Clear any previous errors.
+  void *Fn = dlsym(RTLD_DEFAULT, FnName);
+  if (Fn == nullptr) {
+    if (WarnIfMissing) {
+      const char *ErrorMsg = dlerror();
+      Printf("WARNING: Failed to find function \"%s\".", FnName);
+      if (ErrorMsg)
+        Printf(" Reason %s.", ErrorMsg);
+      Printf("\n");
+    }
+  }
+  return reinterpret_cast<T>(Fn);
+}
+
+namespace fuzzer {
+
+ExternalFunctions::ExternalFunctions() {
+#define EXT_FUNC(NAME, RETURN_TYPE, FUNC_SIG, WARN)                            \
+  this->NAME = GetFnPtr<decltype(ExternalFunctions::NAME)>(#NAME, WARN)
+
+#include "FuzzerExtFunctions.def"
+
+#undef EXT_FUNC
+}
+} // namespace fuzzer
+#endif // LIBFUZZER_APPLE

lib/Fuzzer/FuzzerExtFunctionsWeak.cpp

@@ -0,0 +1,50 @@
+//===- FuzzerExtFunctionsWeak.cpp - Interface to external functions -------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+// Implementation for Linux. This relies on the linker's support for weak
+// symbols. We don't use this approach on Apple platforms because it requires
+// clients of LibFuzzer to pass ``-U _<symbol_name>`` to the linker to allow
+// weak symbols to be undefined. That is a complication we don't want to expose
+// to clients right now.
+//===----------------------------------------------------------------------===//
+#include "FuzzerInternal.h"
+#if LIBFUZZER_LINUX
+
+#include "FuzzerExtFunctions.h"
+
+extern "C" {
+// Declare these symbols as weak to allow them to be optionally defined.
+#define EXT_FUNC(NAME, RETURN_TYPE, FUNC_SIG, WARN)                            \
+  __attribute__((weak)) RETURN_TYPE NAME FUNC_SIG
+
+#include "FuzzerExtFunctions.def"
+
+#undef EXT_FUNC
+}
+
+using namespace fuzzer;
+
+static void CheckFnPtr(void *FnPtr, const char *FnName, bool WarnIfMissing) {
+  if (FnPtr == nullptr && WarnIfMissing) {
+    Printf("WARNING: Failed to find function \"%s\".\n", FnName);
+  }
+}
+
+namespace fuzzer {
+
+ExternalFunctions::ExternalFunctions() {
+#define EXT_FUNC(NAME, RETURN_TYPE, FUNC_SIG, WARN)                            \
+  this->NAME = ::NAME;                                                         \
+  CheckFnPtr((void *)::NAME, #NAME, WARN);
+
+#include "FuzzerExtFunctions.def"
+
+#undef EXT_FUNC
+}
+} // namespace fuzzer
+#endif // LIBFUZZER_LINUX

lib/Fuzzer/FuzzerInternal.h

@@ -25,6 +25,7 @@
 #include <unordered_set>
 #include <vector>
 
+#include "FuzzerExtFunctions.h"
 #include "FuzzerInterface.h"
 #include "FuzzerTracePC.h"
 
@@ -42,7 +43,7 @@
 namespace fuzzer {
 
 typedef int (*UserCallback)(const uint8_t *Data, size_t Size);
-int FuzzerDriver(int argc, char **argv, UserCallback Callback);
+int FuzzerDriver(int *argc, char ***argv, UserCallback Callback);
 
 using namespace std::chrono;
 typedef std::vector<uint8_t> Unit;
@@ -468,6 +469,9 @@ class Fuzzer {
 
   // Need to know our own thread.
   static thread_local bool IsMyThread;
+
+  // Interface to functions that may or may not be available.
+  ExternalFunctions EF;
 };
 
 }; // namespace fuzzer

lib/Fuzzer/FuzzerLoop.cpp

@@ -47,9 +47,6 @@ __sanitizer_update_counter_bitset_and_clear_counters(uint8_t *bitset);
 __attribute__((weak)) uintptr_t
 __sanitizer_get_coverage_pc_buffer(uintptr_t **data);
 
-__attribute__((weak)) size_t LLVMFuzzerCustomMutator(uint8_t *Data, size_t Size,
-                                                     size_t MaxSize,
-                                                     unsigned int Seed);
 __attribute__((weak)) void __sanitizer_malloc_hook(void *ptr, size_t size);
 __attribute__((weak)) void __sanitizer_free_hook(void *ptr);
 __attribute__((weak)) void __lsan_enable();
@@ -695,9 +692,9 @@ void Fuzzer::MutateAndTestOne() {
 
   for (int i = 0; i < Options.MutateDepth; i++) {
     size_t NewSize = 0;
-    if (LLVMFuzzerCustomMutator)
-      NewSize = LLVMFuzzerCustomMutator(CurrentUnitData, Size,
-                                        Options.MaxLen, MD.GetRand().Rand());
+    if (EF.LLVMFuzzerCustomMutator)
+      NewSize = EF.LLVMFuzzerCustomMutator(CurrentUnitData, Size,
+                                           Options.MaxLen, MD.GetRand().Rand());
     else
       NewSize = MD.Mutate(CurrentUnitData, Size, Options.MaxLen);
     assert(NewSize > 0 && "Mutator returned empty unit");

lib/Fuzzer/FuzzerMain.cpp

@@ -15,12 +15,8 @@
 extern "C" {
 // This function should be defined by the user.
 int LLVMFuzzerTestOneInput(const uint8_t *Data, size_t Size);
-// This function may optionally be defined by the user.
-__attribute__((weak)) int LLVMFuzzerInitialize(int *argc, char ***argv);
 }  // extern "C"
 
 int main(int argc, char **argv) {
-  if (LLVMFuzzerInitialize)
-    LLVMFuzzerInitialize(&argc, &argv);
-  return fuzzer::FuzzerDriver(argc, argv, LLVMFuzzerTestOneInput);
+  return fuzzer::FuzzerDriver(&argc, &argv, LLVMFuzzerTestOneInput);
 }