Support inline functions symbolization in Addr2Line symbolizer.

Patch by Maxim Ostapenko!

Summary:
Right now, Addr2Line symbolizer in asan_symbolize.py doesn't support inline functions symbolization. This might be a useful feature for using ASan on embedded systems.

Test results:

$ cat test.c

static inline void FooBarBaz() {
  __sanitizer_print_stack_trace();
}

int main() {
  FooBarBaz();
  return 0;
}

$ clang  test.c -fsanitize=address -g -O2 -o test.x && ./test.x &> /tmp/test.log
$ ./projects/compiler-rt/lib/asan/scripts/asan_symbolize.py  -l /tmp/test.log
    #0 0x42095e in __sanitizer_print_stack_trace _asan_rtl_
    #1 0x4cec07 in FooBarBaz /home/max/build/llvm/asan/test.c:4
    #2 0x4cec07 in main /home/max/build/llvm/asan/test.c:8
    #3 0x7f89f0891ec4 in __libc_start_main /build/buildd/eglibc-2.19/csu/libc-start.c:287

Reviewers: glider, samsonov

Subscribers: jevinskie, llvm-commits, ygribov

Differential Revision: http://reviews.llvm.org/D12153

llvm-svn: 247642

compiler-rt/lib/asan/scripts/asan_symbolize.py

@@ -135,12 +135,13 @@ class Addr2LineSymbolizer(Symbolizer):
     super(Addr2LineSymbolizer, self).__init__()
     self.binary = binary
     self.pipe = self.open_addr2line()
+    self.output_terminator = -1
 
   def open_addr2line(self):
     addr2line_tool = 'addr2line'
     if binutils_prefix:
       addr2line_tool = binutils_prefix + addr2line_tool
-    cmd = [addr2line_tool, '-f']
+    cmd = [addr2line_tool, '-fi']
     if demangle:
       cmd += ['--demangle']
     cmd += ['-e', self.binary]
@@ -153,16 +154,23 @@ class Addr2LineSymbolizer(Symbolizer):
     """Overrides Symbolizer.symbolize."""
     if self.binary != binary:
       return None
+    lines = []
     try:
       print >> self.pipe.stdin, offset
-      function_name = self.pipe.stdout.readline().rstrip()
-      file_name = self.pipe.stdout.readline().rstrip()
+      print >> self.pipe.stdin, self.output_terminator
+      is_first_frame = True
+      while True:
+        function_name = self.pipe.stdout.readline().rstrip()
+        file_name = self.pipe.stdout.readline().rstrip()
+        if is_first_frame:
+          is_first_frame = False
+        elif function_name == '??':
+          assert file_name == '??:0'
+          break
+        lines.append((function_name, file_name));
     except Exception:
-      function_name = ''
-      file_name = ''
-    file_name = fix_filename(file_name)
-    return ['%s in %s %s' % (addr, function_name, file_name)]
-
+      lines.append(('??', '??:0'))
+    return ['%s in %s %s' % (addr, function, fix_filename(file)) for (function, file) in lines]
 
 class UnbufferedLineConverter(object):
   """

compiler-rt/lib/sanitizer_common/sanitizer_symbolizer_internal.h

@@ -88,10 +88,11 @@ class SymbolizerProcess {
     UNIMPLEMENTED();
   }
 
+  virtual bool ReadFromSymbolizer(char *buffer, uptr max_length);
+
  private:
   bool Restart();
   const char *SendCommandImpl(const char *command);
-  bool ReadFromSymbolizer(char *buffer, uptr max_length);
   bool WriteToSymbolizer(const char *buffer, uptr length);
   bool StartSymbolizerSubprocess();
 

compiler-rt/lib/sanitizer_common/sanitizer_symbolizer_posix_libcdep.cc

@@ -194,30 +194,54 @@ class Addr2LineProcess : public SymbolizerProcess {
   const char *module_name() const { return module_name_; }
 
  private:
-  bool ReachedEndOfOutput(const char *buffer, uptr length) const override {
-    // Output should consist of two lines.
-    int num_lines = 0;
-    for (uptr i = 0; i < length; ++i) {
-      if (buffer[i] == '\n')
-        num_lines++;
-      if (num_lines >= 2)
-        return true;
-    }
-    return false;
-  }
-
   void GetArgV(const char *path_to_binary,
                const char *(&argv)[kArgVMax]) const override {
     int i = 0;
     argv[i++] = path_to_binary;
-    argv[i++] = "-Cfe";
+    argv[i++] = "-iCfe";
     argv[i++] = module_name_;
     argv[i++] = nullptr;
   }
 
+  bool ReachedEndOfOutput(const char *buffer, uptr length) const override;
+
+  bool ReadFromSymbolizer(char *buffer, uptr max_length) override {
+    if (!SymbolizerProcess::ReadFromSymbolizer(buffer, max_length))
+      return false;
+    // We should cut out output_terminator_ at the end of given buffer,
+    // appended by addr2line to mark the end of its meaningful output.
+    // We cannot scan buffer from it's beginning, because it is legal for it
+    // to start with output_terminator_ in case given offset is invalid. So,
+    // scanning from second character.
+    char *garbage = internal_strstr(buffer + 1, output_terminator_);
+    // This should never be NULL since buffer must end up with
+    // output_terminator_.
+    CHECK(garbage);
+    // Trim the buffer.
+    garbage[0] = '\0';
+    return true;
+  }
+
   const char *module_name_;  // Owned, leaked.
+  static const char output_terminator_[];
 };
 
+const char Addr2LineProcess::output_terminator_[] = "??\n??:0\n";
+
+bool Addr2LineProcess::ReachedEndOfOutput(const char *buffer,
+                                          uptr length) const {
+  const size_t kTerminatorLen = sizeof(output_terminator_) - 1;
+  // Skip, if we read just kTerminatorLen bytes, because Addr2Line output
+  // should consist at least of two pairs of lines:
+  // 1. First one, corresponding to given offset to be symbolized
+  // (may be equal to output_terminator_, if offset is not valid).
+  // 2. Second one for output_terminator_, itself to mark the end of output.
+  if (length <= kTerminatorLen) return false;
+  // Addr2Line output should end up with output_terminator_.
+  return !internal_memcmp(buffer + length - kTerminatorLen,
+                          output_terminator_, kTerminatorLen);
+}
+
 class Addr2LinePool : public SymbolizerTool {
  public:
   explicit Addr2LinePool(const char *addr2line_path,
@@ -254,15 +278,18 @@ class Addr2LinePool : public SymbolizerTool {
       addr2line_pool_.push_back(addr2line);
     }
     CHECK_EQ(0, internal_strcmp(module_name, addr2line->module_name()));
-    char buffer_[kBufferSize];
-    internal_snprintf(buffer_, kBufferSize, "0x%zx\n", module_offset);
-    return addr2line->SendCommand(buffer_);
+    char buffer[kBufferSize];
+    internal_snprintf(buffer, kBufferSize, "0x%zx\n0x%zx\n",
+                      module_offset, dummy_address_);
+    return addr2line->SendCommand(buffer);
   }
 
-  static const uptr kBufferSize = 32;
+  static const uptr kBufferSize = 64;
   const char *addr2line_path_;
   LowLevelAllocator *allocator_;
   InternalMmapVector<Addr2LineProcess*> addr2line_pool_;
+  static const uptr dummy_address_ =
+      FIRST_32_SECOND_64(UINT32_MAX, UINT64_MAX);
 };
 
 #if SANITIZER_SUPPORTS_WEAK_HOOKS