[libFuzzer] Use octal instead of hex escape sequences in PrintASCII

Previously, PrintASCII would print the string "\ta" as "\x09a". However,
in C/C++ those strings are not the same: the trailing 'a' is part of the
escape sequence, which means it's equivalent to "\x9a". This is an
annoying quirk of the standard. (See
https://eel.is/c++draft/lex.ccon#nt:hexadecimal-escape-sequence)

To fix this, output three-digit octal escape sequences instead. Since
octal escapes are limited to max three digits, this avoids the problem
of subsequent characters unintentionally becoming part of the escape
sequence.

Dictionary files still use the non-C-compatible hex escapes, but I
believe we can't change the format since it comes from AFL, and
libfuzzer never writes such files, it only has to read them, so they're
not affected by this change.

Differential revision: https://reviews.llvm.org/D110920

diff --git a/compiler-rt/lib/fuzzer/FuzzerIO.cpp b/compiler-rt/lib/fuzzer/FuzzerIO.cpp
index d77c65c..0a58c53 100644 (file)
--- a/compiler-rt/lib/fuzzer/FuzzerIO.cpp
+++ b/compiler-rt/lib/fuzzer/FuzzerIO.cpp
@@ -23,6 +23,14 @@ namespace fuzzer {
 
 static FILE *OutputFile = stderr;
 
+FILE *GetOutputFile() {
+  return OutputFile;
+}
+
+void SetOutputFile(FILE *NewOutputFile) {
+  OutputFile = NewOutputFile;
+}
+
 long GetEpoch(const std::string &Path) {
   struct stat St;
   if (stat(Path.c_str(), &St))

diff --git a/compiler-rt/lib/fuzzer/FuzzerIO.h b/compiler-rt/lib/fuzzer/FuzzerIO.h
index 33ac20e..401afa0 100644 (file)
--- a/compiler-rt/lib/fuzzer/FuzzerIO.h
+++ b/compiler-rt/lib/fuzzer/FuzzerIO.h
@@ -54,6 +54,10 @@ void DupAndCloseStderr();
 
 void CloseStdout();
 
+// For testing.
+FILE *GetOutputFile();
+void SetOutputFile(FILE *NewOutputFile);
+
 void Printf(const char *Fmt, ...);
 void VPrintf(bool Verbose, const char *Fmt, ...);
 

diff --git a/compiler-rt/lib/fuzzer/FuzzerUtil.cpp b/compiler-rt/lib/fuzzer/FuzzerUtil.cpp
index d82bdcd..aeab70f 100644 (file)
--- a/compiler-rt/lib/fuzzer/FuzzerUtil.cpp
+++ b/compiler-rt/lib/fuzzer/FuzzerUtil.cpp
@@ -43,7 +43,7 @@ void PrintASCIIByte(uint8_t Byte) {
   else if (Byte >= 32 && Byte < 127)
     Printf("%c", Byte);
   else
-    Printf("\\x%02x", Byte);
+    Printf("\\%03o", Byte);
 }
 
 void PrintASCII(const uint8_t *Data, size_t Size, const char *PrintAfter) {

diff --git a/compiler-rt/lib/fuzzer/tests/FuzzerUnittest.cpp b/compiler-rt/lib/fuzzer/tests/FuzzerUnittest.cpp
index 1b0e734..accbaaa 100644 (file)
--- a/compiler-rt/lib/fuzzer/tests/FuzzerUnittest.cpp
+++ b/compiler-rt/lib/fuzzer/tests/FuzzerUnittest.cpp
@@ -591,6 +591,42 @@ TEST(FuzzerUtil, Base64) {
   EXPECT_EQ("YWJjeHl6", Base64({'a', 'b', 'c', 'x', 'y', 'z'}));
 }
 
+#ifdef __GLIBC__
+class PrintfCapture {
+ public:
+  PrintfCapture() {
+    OldOutputFile = GetOutputFile();
+    SetOutputFile(open_memstream(&Buffer, &Size));
+  }
+  ~PrintfCapture() {
+    fclose(GetOutputFile());
+    SetOutputFile(OldOutputFile);
+    free(Buffer);
+  }
+  std::string str() { return std::string(Buffer, Size); }
+
+ private:
+  char *Buffer;
+  size_t Size;
+  FILE *OldOutputFile;
+};
+
+TEST(FuzzerUtil, PrintASCII) {
+  auto f = [](const char *Str, const char *PrintAfter = "") {
+    PrintfCapture Capture;
+    PrintASCII(reinterpret_cast<const uint8_t*>(Str), strlen(Str), PrintAfter);
+    return Capture.str();
+  };
+  EXPECT_EQ("hello", f("hello"));
+  EXPECT_EQ("c:\\\\", f("c:\\"));
+  EXPECT_EQ("\\\"hi\\\"", f("\"hi\""));
+  EXPECT_EQ("\\011a", f("\ta"));
+  EXPECT_EQ("\\0111", f("\t1"));
+  EXPECT_EQ("hello\\012", f("hello\n"));
+  EXPECT_EQ("hello\n", f("hello", "\n"));
+}
+#endif
+
 TEST(Corpus, Distribution) {
   DataFlowTrace DFT;
   Random Rand(0);