[tsan] Add global symbolication support into AtosSymbolizer

[kubamracek]

Summary

This patch adds support for symbolication of globals (implements SymbolizeData) for AtosSymbolizer on OS X.

[kubamracek]

Adding a testcase.

[samsonov]

LGTM

compiler-rt/trunk/lib/sanitizer_common/sanitizer_symbolizer_mac.cc

static bool IsAtosErrorMessage(const char *str) {
   for (uptr i = 0; i < ARRAY_SIZE(kAtosErrorMessages); i++) {
     if (internal_strstr(str, kAtosErrorMessages[i])) {
       return true;
     }
   }
   return false;
 }
 
-static bool ParseCommandOutput(const char *str, SymbolizedStack *res) {
+static bool ParseCommandOutput(const char *str, uptr addr, char **out_name,
+                               char **out_module, char **out_file, uptr *line,
+                               uptr *start_address) {
   // Trim ending newlines.
   char *trim;
   ExtractTokenUpToDelimiter(str, "\n", &trim);
 
   // The line from `atos` is in one of these formats:
   //   myfunction (in library.dylib) (sourcefile.c:17)
   //   myfunction (in library.dylib) + 0x1fe
+  //   myfunction (in library.dylib) + 15
   //   0xdeadbeef (in library.dylib) + 0x1fe
+  //   0xdeadbeef (in library.dylib) + 15
   //   0xdeadbeef (in library.dylib)
   //   0xdeadbeef
 
   if (IsAtosErrorMessage(trim)) {
     Report("atos returned an error: %s\n", trim);
     InternalFree(trim);
     return false;
   }
 
   const char *rest = trim;
-  char *function_name;
-  rest = ExtractTokenUpToDelimiter(rest, " (in ", &function_name);
-  if (internal_strncmp(function_name, "0x", 2) != 0)
-    res->info.function = function_name;
+  char *symbol_name;
+  rest = ExtractTokenUpToDelimiter(rest, " (in ", &symbol_name);
+  if (internal_strncmp(symbol_name, "0x", 2) != 0)
+    *out_name = symbol_name;
   else
-    InternalFree(function_name);
-  rest = ExtractTokenUpToDelimiter(rest, ") ", &res->info.module);
+    InternalFree(symbol_name);
+  rest = ExtractTokenUpToDelimiter(rest, ") ", out_module);
 
   if (rest[0] == '(') {
+    if (out_file) {
       rest++;
-    rest = ExtractTokenUpToDelimiter(rest, ":", &res->info.file);
+      rest = ExtractTokenUpToDelimiter(rest, ":", out_file);
       char *extracted_line_number;
       rest = ExtractTokenUpToDelimiter(rest, ")", &extracted_line_number);
-    res->info.line = internal_atoll(extracted_line_number);
+      if (line) *line = (uptr)internal_atoll(extracted_line_number);
       InternalFree(extracted_line_number);
     }
+  } else if (rest[0] == '+') {
+    rest += 2;
+    uptr offset = internal_atoll(rest);
+    if (start_address) *start_address = addr - offset;
+  }
 
   InternalFree(trim);
   return true;
 }
 
 AtosSymbolizer::AtosSymbolizer(const char *path, LowLevelAllocator *allocator)
     : process_(new(*allocator) AtosSymbolizerProcess(path, getpid())) {}
 
 bool AtosSymbolizer::SymbolizePC(uptr addr, SymbolizedStack *stack) {
   if (!process_) return false;
   char command[32];
   internal_snprintf(command, sizeof(command), "0x%zx\n", addr);
   const char *buf = process_->SendCommand(command);
   if (!buf) return false;
-  if (!ParseCommandOutput(buf, stack)) {
+  uptr line;
+  if (!ParseCommandOutput(buf, addr, &stack->info.function, &stack->info.module,
+                          &stack->info.file, &line, nullptr)) {
     process_ = nullptr;
     return false;
   }
+  stack->info.line = (int)line;
   return true;
 }
 
-bool AtosSymbolizer::SymbolizeData(uptr addr, DataInfo *info) { return false; }
+bool AtosSymbolizer::SymbolizeData(uptr addr, DataInfo *info) {
+  if (!process_) return false;
+  char command[32];
+  internal_snprintf(command, sizeof(command), "0x%zx\n", addr);
+  const char *buf = process_->SendCommand(command);
+  if (!buf) return false;
+  if (!ParseCommandOutput(buf, addr, &info->name, &info->module, nullptr,
+                          nullptr, &info->start)) {
+    process_ = nullptr;
+    return false;
+  }
+  return true;
+}
 
 }  // namespace __sanitizer
 
 #endif  // SANITIZER_MAC

compiler-rt/trunk/test/tsan/Darwin/symbolizer-atos.cc

+// RUN: %clangxx_tsan %s -o %t
+// RUN: TSAN_OPTIONS=$TSAN_OPTIONS:verbosity=2:external_symbolizer_path=/usr/bin/atos %deflake %run %t | FileCheck %s
+#include "../test.h"
+
+int GlobalData[10];
+
+void *Thread(void *a) {
+  barrier_wait(&barrier);
+  GlobalData[2] = 42;
+  return 0;
+}
+
+int main() {
+  barrier_init(&barrier, 2);
+  fprintf(stderr, "addr=");
+  print_address(GlobalData);
+  fprintf(stderr, "\n");
+  pthread_t t;
+  pthread_create(&t, 0, Thread, 0);
+  GlobalData[2] = 43;
+  barrier_wait(&barrier);
+  pthread_join(t, 0);
+}
+
+// CHECK: Using atos at user-specified path: /usr/bin/atos
+// CHECK: addr=[[ADDR:0x[0-9,a-f]+]]
+// CHECK: WARNING: ThreadSanitizer: data race
+// CHECK: Location is global 'GlobalData' at [[ADDR]] ({{.*}}+0x{{[0-9,a-f]+}})