[compiler-rt] Some clean up / refactoring in sanitizer_symbolizer_libcdep.cpp.

[Dor1s]

Summary

Nothing critical, just a few potential improvements I've noticed while reading
the code:

• return false when symbolizer buffer is too small to read all data
• invert some conditions to reduce indentation
• prefer nullptr over 0 for pointers; init some pointers on stack;
• remove minor code duplication

[Dor1s]

Looks like there is potentially relevant failure in: http://lab.llvm.org:8011/builders/clang-ppc64le-linux/builds/29265

Will wait a bit longer and may have to revert then :|

compiler-rt/lib/sanitizer_common/sanitizer_symbolizer_libcdep.cpp

const char *ExtractToken(const char *str, const char *delims, char **result) {
   internal_memcpy(*result, str, prefix_len);
   (*result)[prefix_len] = '\0';
   const char *prefix_end = str + prefix_len;
   if (*prefix_end != '\0') prefix_end++;
   return prefix_end;
 }
 
 const char *ExtractInt(const char *str, const char *delims, int *result) {
-  char *buff;
+  char *buff = nullptr;
   const char *ret = ExtractToken(str, delims, &buff);
-  if (buff != 0) {
+  if (buff) {
     *result = (int)internal_atoll(buff);
   }
   InternalFree(buff);
   return ret;
 }
 
 const char *ExtractUptr(const char *str, const char *delims, uptr *result) {
-  char *buff;
+  char *buff = nullptr;
   const char *ret = ExtractToken(str, delims, &buff);
-  if (buff != 0) {
+  if (buff) {
     *result = (uptr)internal_atoll(buff);
   }
   InternalFree(buff);
   return ret;
 }
 
 const char *ExtractSptr(const char *str, const char *delims, sptr *result) {
-  char *buff;
+  char *buff = nullptr;
   const char *ret = ExtractToken(str, delims, &buff);
-  if (buff != 0) {
+  if (buff) {
     *result = (sptr)internal_atoll(buff);
   }
   InternalFree(buff);
   return ret;
 }
 
 const char *ExtractTokenUpToDelimiter(const char *str, const char *delimiter,
                                       char **result) {
   const char *found_delimiter = internal_strstr(str, delimiter);
   uptr prefix_len =
       found_delimiter ? found_delimiter - str : internal_strlen(str);
   *result = (char *)InternalAlloc(prefix_len + 1);
   internal_memcpy(*result, str, prefix_len);
   (*result)[prefix_len] = '\0';
   const char *prefix_end = str + prefix_len;
   if (*prefix_end != '\0') prefix_end += internal_strlen(delimiter);
   return prefix_end;
 }
 
 SymbolizedStack *Symbolizer::SymbolizePC(uptr addr) {
   BlockingMutexLock l(&mu_);
-  const char *module_name;
+  const char *module_name = nullptr;
   uptr module_offset;
   ModuleArch arch;
   SymbolizedStack *res = SymbolizedStack::New(addr);
   if (!FindModuleNameAndOffsetForAddress(addr, &module_name, &module_offset,
                                          &arch))
     return res;
   // Always fill data about module name and offset.
   res->info.FillModuleInfo(module_name, module_offset, arch);
   for (auto &tool : tools_) {
     SymbolizerScope sym_scope(this);
     if (tool.SymbolizePC(addr, res)) {
       return res;
     }
   }
   return res;
 }
 
 bool Symbolizer::SymbolizeData(uptr addr, DataInfo *info) {
   BlockingMutexLock l(&mu_);
-  const char *module_name;
+  const char *module_name = nullptr;
   uptr module_offset;
   ModuleArch arch;
   if (!FindModuleNameAndOffsetForAddress(addr, &module_name, &module_offset,
                                          &arch))
     return false;
   info->Clear();
   info->module = internal_strdup(module_name);
   info->module_offset = module_offset;
   info->module_arch = arch;
   for (auto &tool : tools_) {
     SymbolizerScope sym_scope(this);
     if (tool.SymbolizeData(addr, info)) {
       return true;
     }
   }
   return true;
 }
 
 bool Symbolizer::SymbolizeFrame(uptr addr, FrameInfo *info) {
   BlockingMutexLock l(&mu_);
-  const char *module_name;
+  const char *module_name = nullptr;
   if (!FindModuleNameAndOffsetForAddress(
           addr, &module_name, &info->module_offset, &info->module_arch))
     return false;
   info->module = internal_strdup(module_name);
   for (auto &tool : tools_) {
     SymbolizerScope sym_scope(this);
     if (tool.SymbolizeFrame(addr, info)) {
       return true;
const char *Symbolizer::Demangle(const char *name) {
   return PlatformDemangle(name);
 }
 
 bool Symbolizer::FindModuleNameAndOffsetForAddress(uptr address,
                                                    const char **module_name,
                                                    uptr *module_offset,
                                                    ModuleArch *module_arch) {
   const LoadedModule *module = FindModuleForAddress(address);
-  if (module == nullptr)
+  if (!module)
     return false;
   *module_name = module->full_name();
   *module_offset = address - module->base_address();
   *module_arch = module->arch();
   return true;
 }
 
 void Symbolizer::RefreshModules() {

 
 LLVMSymbolizer::LLVMSymbolizer(const char *path, LowLevelAllocator *allocator)
     : symbolizer_process_(new(*allocator) LLVMSymbolizerProcess(path)) {}
 
 // Parse a <file>:<line>[:<column>] buffer. The file path may contain colons on
 // Windows, so extract tokens from the right hand side first. The column info is
 // also optional.
 static const char *ParseFileLineInfo(AddressInfo *info, const char *str) {
-  char *file_line_info = 0;
+  char *file_line_info = nullptr;
   str = ExtractToken(str, "\n", &file_line_info);
   CHECK(file_line_info);
 
   if (uptr size = internal_strlen(file_line_info)) {
     char *back = file_line_info + size - 1;
     for (int i = 0; i < 2; ++i) {
       while (back > file_line_info && IsDigit(*back)) --back;
       if (*back != ':' || !IsDigit(back[1])) break;

 //   <function_name>
 //   <file_name>:<line_number>[:<column_number>]
 // Used by LLVMSymbolizer, Addr2LinePool and InternalSymbolizer, since all of
 // them use the same output format.
 void ParseSymbolizePCOutput(const char *str, SymbolizedStack *res) {
   bool top_frame = true;
   SymbolizedStack *last = res;
   while (true) {
-    char *function_name = 0;
+    char *function_name = nullptr;
     str = ExtractToken(str, "\n", &function_name);
     CHECK(function_name);
     if (function_name[0] == '\0') {
       // There are no more frames.
       InternalFree(function_name);
       break;
     }
     SymbolizedStack *cur;
while (*str) {
     locals->push_back(local);
   }
 }
 
 bool LLVMSymbolizer::SymbolizePC(uptr addr, SymbolizedStack *stack) {
   AddressInfo *info = &stack->info;
   const char *buf = FormatAndSendCommand(
       "CODE", info->module, info->module_offset, info->module_arch);
-  if (buf) {
-    ParseSymbolizePCOutput(buf, stack);
-    return true;
-  }
-  return false;
-}
+  if (!buf)
+    return false;
 
 bool LLVMSymbolizer::SymbolizeData(uptr addr, DataInfo *info) {
   const char *buf = FormatAndSendCommand(
       "DATA", info->module, info->module_offset, info->module_arch);
-  if (buf) {
-    ParseSymbolizeDataOutput(buf, info);
-    info->start += (addr - info->module_offset); // Add the base address.
-    return true;
-  }
-  return false;
-}
+  if (!buf)
+    return false;
 
 bool LLVMSymbolizer::SymbolizeFrame(uptr addr, FrameInfo *info) {
   const char *buf = FormatAndSendCommand(
       "FRAME", info->module, info->module_offset, info->module_arch);
-  if (buf) {
-    ParseSymbolizeFrameOutput(buf, &info->locals);
-    return true;
-  }
-  return false;
-}
+  if (!buf)
+    return false;
 
 const char *LLVMSymbolizer::FormatAndSendCommand(const char *command_prefix,
                                                  const char *module_name,
                                                  uptr module_offset,
                                                  ModuleArch arch) {
   CHECK(module_name);
-  if (arch == kModuleArchUnknown) {
-    if (internal_snprintf(buffer_, kBufferSize, "%s \"%s\" 0x%zx\n",
-                          command_prefix, module_name,
-                          module_offset) >= static_cast<int>(kBufferSize)) {
-      Report("WARNING: Command buffer too small");
-      return nullptr;
-    }
-  } else {
-    if (internal_snprintf(buffer_, kBufferSize, "%s \"%s:%s\" 0x%zx\n",
-                          command_prefix, module_name, ModuleArchToString(arch),
-                          module_offset) >= static_cast<int>(kBufferSize)) {
-      Report("WARNING: Command buffer too small");
-      return nullptr;
-    }
-  }
+  int size_needed = 0;
+  if (arch == kModuleArchUnknown)
+    size_needed = internal_snprintf(buffer_, kBufferSize, "%s \"%s\" 0x%zx\n",
+                                    command_prefix, module_name, module_offset);
+  else
+    size_needed = internal_snprintf(buffer_, kBufferSize,
+                                    "%s \"%s:%s\" 0x%zx\n", command_prefix,
+                                    module_name, ModuleArchToString(arch),
+                                    module_offset);
+
+  if (size_needed >= static_cast<int>(kBufferSize)) {
+
   return symbolizer_process_->SendCommand(buffer_);
 }
 
 SymbolizerProcess::SymbolizerProcess(const char *path, bool use_posix_spawn)
     : path_(path),
       input_fd_(kInvalidFd),
       output_fd_(kInvalidFd),
       times_restarted_(0),
for (; times_restarted_ < kMaxTimesRestarted; times_restarted_++) {
     if (const char *res = SendCommandImpl(command))
       return res;
     Restart();
   }
   if (!failed_to_start_) {
     Report("WARNING: Failed to use and restart external symbolizer!\n");
     failed_to_start_ = true;
   }
-  return 0;
+  return nullptr;
 }
 
 const char *SymbolizerProcess::SendCommandImpl(const char *command) {
   if (input_fd_ == kInvalidFd || output_fd_ == kInvalidFd)
-      return 0;
+      return nullptr;
   if (!WriteToSymbolizer(command, internal_strlen(command)))
-      return 0;
+      return nullptr;
   if (!ReadFromSymbolizer(buffer_, kBufferSize))
-      return 0;
+      return nullptr;
   return buffer_;
 }
 
 bool SymbolizerProcess::Restart() {
   if (input_fd_ != kInvalidFd)
     CloseFile(input_fd_);
   if (output_fd_ != kInvalidFd)
     CloseFile(output_fd_);
if (!success || just_read == 0) {
       Report("WARNING: Can't read from symbolizer at fd %d\n", input_fd_);
       return false;
     }
     read_len += just_read;
     if (ReachedEndOfOutput(buffer, read_len))
       break;
     if (read_len + 1 == max_length) {
       Report("WARNING: Symbolizer buffer too small\n");
-      read_len = 0;
-      break;
+      buffer[0] = '\0';
+      return false;
     }
   }
   buffer[read_len] = '\0';
   return true;
 }
 
 bool SymbolizerProcess::WriteToSymbolizer(const char *buffer, uptr length) {
   if (length == 0)