llvm-mc-fuzzer: A fuzzing tool for the MC layer.

Summary:
Only the disassembler is supported in this patch but it has already found a few
issues in the Mips disassembler (mostly invalid instructions being successfully
disassembled).

Reviewers: kcc

Subscribers: russell.gallop, silvas, kcc, llvm-commits

Differential Revision: http://reviews.llvm.org/D12723

llvm-svn: 247786

llvm/docs/LibFuzzer.rst

@@ -453,7 +453,14 @@ Trophies
 
   * llvm-as: https://llvm.org/bugs/show_bug.cgi?id=24639
 
-
+  * Disassembler:
+    * Mips: Discovered a number of untested instructions for the Mips target
+      (see valid-mips*.s in http://reviews.llvm.org/rL247405,
+      http://reviews.llvm.org/rL247414, http://reviews.llvm.org/rL247416,
+      http://reviews.llvm.org/rL247417, http://reviews.llvm.org/rL247420,
+      and http://reviews.llvm.org/rL247422) as well some instructions that
+      successfully disassembled on ISA's where they were not valid (see
+      invalid-xfail.s files in the same commits).
 
 .. _pcre2: http://www.pcre.org/
 

llvm/tools/llvm-mc-fuzzer/CMakeLists.txt

@@ -0,0 +1,18 @@
+if( LLVM_USE_SANITIZE_COVERAGE )
+  include_directories(BEFORE
+    ${CMAKE_CURRENT_SOURCE_DIR}/../../lib/Fuzzer)
+
+  set(LLVM_LINK_COMPONENTS
+      AllTargetsDescs
+      AllTargetsDisassemblers
+      AllTargetsInfos
+      MC
+      MCDisassembler
+      Support
+      )
+  add_llvm_tool(llvm-mc-fuzzer 
+                llvm-mc-fuzzer.cpp)
+  target_link_libraries(llvm-mc-fuzzer
+                        LLVMFuzzerNoMain
+                        )
+endif()

llvm/tools/llvm-mc-fuzzer/llvm-mc-fuzzer.cpp

@@ -0,0 +1,129 @@
+//===--- llvm-mc-fuzzer.cpp - Fuzzer for the MC layer ---------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm-c/Disassembler.h"
+#include "llvm-c/Target.h"
+#include "llvm/ADT/ArrayRef.h"
+#include "llvm/MC/SubtargetFeature.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/raw_ostream.h"
+#include "FuzzerInterface.h"
+
+using namespace llvm;
+
+const unsigned AssemblyTextBufSize = 80;
+
+enum ActionType {
+  AC_Assemble,
+  AC_Disassemble
+};
+
+static cl::opt<ActionType>
+Action(cl::desc("Action to perform:"),
+       cl::init(AC_Assemble),
+       cl::values(clEnumValN(AC_Assemble, "assemble",
+                             "Assemble a .s file (default)"),
+                  clEnumValN(AC_Disassemble, "disassemble",
+                             "Disassemble strings of hex bytes"),
+                  clEnumValEnd));
+
+static cl::opt<std::string>
+    TripleName("triple", cl::desc("Target triple to assemble for, "
+                                  "see -version for available targets"));
+
+static cl::opt<std::string>
+    MCPU("mcpu",
+         cl::desc("Target a specific cpu type (-mcpu=help for details)"),
+         cl::value_desc("cpu-name"), cl::init(""));
+
+static cl::list<std::string>
+    MAttrs("mattr", cl::CommaSeparated,
+           cl::desc("Target specific attributes (-mattr=help for details)"),
+           cl::value_desc("a1,+a2,-a3,..."));
+// The feature string derived from -mattr's values.
+std::string FeaturesStr;
+
+static cl::list<std::string>
+    FuzzerArgv("fuzzer-args", cl::Positional,
+               cl::desc("Options to pass to the fuzzer"), cl::ZeroOrMore,
+               cl::PositionalEatsArgs);
+
+void DisassembleOneInput(const uint8_t *Data, size_t Size) {
+  char AssemblyText[AssemblyTextBufSize];
+
+  std::vector<uint8_t> DataCopy(Data, Data + Size);
+
+  LLVMDisasmContextRef Ctx = LLVMCreateDisasmCPUFeatures(
+      TripleName.c_str(), MCPU.c_str(), FeaturesStr.c_str(), nullptr, 0,
+      nullptr, nullptr);
+  assert(Ctx);
+  uint8_t *p = DataCopy.data();
+  unsigned Consumed;
+  do {
+    Consumed = LLVMDisasmInstruction(Ctx, p, Size, 0, AssemblyText,
+                                     AssemblyTextBufSize);
+    Size -= Consumed;
+    p += Consumed;
+  } while (Consumed != 0);
+  LLVMDisasmDispose(Ctx);
+}
+
+int main(int argc, char **argv) {
+  // The command line is unusual compared to other fuzzers due to the need to
+  // specify the target. Options like -triple, -mcpu, and -mattr work like
+  // their counterparts in llvm-mc, while -fuzzer-args collects options for the
+  // fuzzer itself.
+  //
+  // Examples:
+  //
+  // Fuzz the big-endian MIPS32R6 disassembler using 100,000 inputs of up to
+  // 4-bytes each and use the contents of ./corpus as the test corpus:
+  //   llvm-mc-fuzzer -triple mips-linux-gnu -mcpu=mips32r6 -disassemble \
+  //       -fuzzer-args -max_len=4 -runs=100000 ./corpus
+  //
+  // Infinitely fuzz the little-endian MIPS64R2 disassembler with the MSA
+  // feature enabled using up to 64-byte inputs:
+  //   llvm-mc-fuzzer -triple mipsel-linux-gnu -mcpu=mips64r2 -mattr=msa \
+  //       -disassemble -fuzzer-args ./corpus
+  //
+  // If your aim is to find instructions that are not tested, then it is
+  // advisable to constrain the maximum input size to a single instruction
+  // using -max_len as in the first example. This results in a test corpus of
+  // individual instructions that test unique paths. Without this constraint,
+  // there will be considerable redundancy in the corpus.
+
+  LLVMInitializeAllTargetInfos();
+  LLVMInitializeAllTargetMCs();
+  LLVMInitializeAllDisassemblers();
+
+  cl::ParseCommandLineOptions(argc, argv);
+
+  // Package up features to be passed to target/subtarget
+  // We have to pass it via a global since the callback doesn't
+  // permit any user data.
+  if (MAttrs.size()) {
+    SubtargetFeatures Features;
+    for (unsigned i = 0; i != MAttrs.size(); ++i)
+      Features.AddFeature(MAttrs[i]);
+    FeaturesStr = Features.getString();
+  }
+
+  // Insert the program name into the FuzzerArgv.
+  FuzzerArgv.insert(FuzzerArgv.begin(), argv[0]);
+
+  if (Action == AC_Assemble)
+    errs() << "error: -assemble is not implemented\n";
+  else if (Action == AC_Disassemble)
+    return fuzzer::FuzzerDriver(FuzzerArgv, DisassembleOneInput);
+
+  llvm_unreachable("Unknown action");
+  return 1;
+}