Provide a fallback __cxa_thread_atexit() implementation. Patch from Tavian Barnes

llvm-svn: 283988

libcxxabi/src/cxa_thread_atexit.cpp

@@ -7,20 +7,133 @@
 //
 //===----------------------------------------------------------------------===//
 
+#include "abort_message.h"
 #include "cxxabi.h"
+#include <cstdlib>
+#include <pthread.h>
 
 namespace __cxxabiv1 {
-extern "C" {
 
-#ifdef HAVE___CXA_THREAD_ATEXIT_IMPL
+  using Dtor = void(*)(void*);
 
-_LIBCXXABI_FUNC_VIS int __cxa_thread_atexit(void (*dtor)(void *), void *obj,
-                                            void *dso_symbol) throw() {
-  extern int __cxa_thread_atexit_impl(void (*)(void *), void *, void *);
-  return __cxa_thread_atexit_impl(dtor, obj, dso_symbol);
-}
+  extern "C"
+#ifndef HAVE___CXA_THREAD_ATEXIT_IMPL
+  // A weak symbol is used to detect this function's presence in the C library
+  // at runtime, even if libc++ is built against an older libc
+  __attribute__((__weak__))
+#endif
+  int __cxa_thread_atexit_impl(Dtor, void*, void*);
+
+#ifndef HAVE___CXA_THREAD_ATEXIT_IMPL
+
+namespace {
+  // This implementation is used if the C library does not provide
+  // __cxa_thread_atexit_impl() for us.  It has a number of limitations that are
+  // difficult to impossible to address without ..._impl():
+  //
+  // - dso_symbol is ignored.  This means that a shared library may be unloaded
+  //   (via dlclose()) before its thread_local destructors have run.
+  //
+  // - thread_local destructors for the main thread are run by the destructor of
+  //   a static object.  This is later than expected; they should run before the
+  //   destructors of any objects with static storage duration.
+  //
+  // - thread_local destructors on non-main threads run on the first iteration
+  //   through the pthread_key destructors.  std::notify_all_at_thread_exit()
+  //   and similar functions must be careful to wait until the second iteration
+  //   to provide their intended ordering guarantees.
+  //
+  // Another limitation, though one shared with ..._impl(), is that any
+  // thread_locals that are first initialized after non-thread_local global
+  // destructors begin to run will not be destroyed.  [basic.start.term] states
+  // that all thread_local destructors are sequenced before the destruction of
+  // objects with static storage duration, resulting in a contradiction if a
+  // thread_local is constructed after that point.  Thus we consider such
+  // programs ill-formed, and don't bother to run those destructors.  (If the
+  // program terminates abnormally after such a thread_local is constructed,
+  // the destructor is not expected to run and thus there is no contradiction.
+  // So construction still has to work.)
+
+  struct DtorList {
+    Dtor dtor;
+    void* obj;
+    DtorList* next;
+  };
+
+  // The linked list of thread-local destructors to run
+  __thread DtorList* dtors = nullptr;
+  // True if the destructors are currently scheduled to run on this thread
+  __thread bool dtors_alive = false;
+  // Used to trigger destructors on thread exit; value is ignored
+  pthread_key_t dtors_key;
+
+  void run_dtors(void*) {
+    while (auto head = dtors) {
+      dtors = head->next;
+      head->dtor(head->obj);
+      std::free(head);
+    }
+
+    dtors_alive = false;
+  }
+
+  struct DtorsManager {
+    DtorsManager() {
+      // There is intentionally no matching pthread_key_delete call, as
+      // __cxa_thread_atexit() may be called arbitrarily late (for example, from
+      // global destructors or atexit() handlers).
+      if (pthread_key_create(&dtors_key, run_dtors) != 0) {
+        abort_message("pthread_key_create() failed in __cxa_thread_atexit()");
+      }
+    }
+
+    ~DtorsManager() {
+      // pthread_key destructors do not run on threads that call exit()
+      // (including when the main thread returns from main()), so we explicitly
+      // call the destructor here.  This runs at exit time (potentially earlier
+      // if libc++abi is dlclose()'d).  Any thread_locals initialized after this
+      // point will not be destroyed.
+      run_dtors(nullptr);
+    }
+  };
+} // namespace
 
 #endif // HAVE__CXA_THREAD_ATEXIT_IMPL
 
+extern "C" {
+
+  _LIBCXXABI_FUNC_VIS int __cxa_thread_atexit(Dtor dtor, void* obj, void* dso_symbol) throw() {
+#ifdef HAVE___CXA_THREAD_ATEXIT_IMPL
+    return __cxa_thread_atexit_impl(dtor, obj, dso_symbol);
+#else
+    if (__cxa_thread_atexit_impl) {
+      return __cxa_thread_atexit_impl(dtor, obj, dso_symbol);
+    } else {
+      // Initialize the dtors pthread_key (uses __cxa_guard_*() for one-time
+      // initialization and __cxa_atexit() for destruction)
+      static DtorsManager manager;
+
+      if (!dtors_alive) {
+        if (pthread_setspecific(dtors_key, &dtors_key) != 0) {
+          return -1;
+        }
+        dtors_alive = true;
+      }
+
+      auto head = static_cast<DtorList*>(std::malloc(sizeof(DtorList)));
+      if (!head) {
+        return -1;
+      }
+
+      head->dtor = dtor;
+      head->obj = obj;
+      head->next = dtors;
+      dtors = head;
+
+      return 0;
+    }
+#endif // HAVE___CXA_THREAD_ATEXIT_IMPL
+  }
+
 } // extern "C"
 } // namespace __cxxabiv1

libcxxabi/test/CMakeLists.txt

@@ -17,7 +17,6 @@ pythonize_bool(LIBCXXABI_ENABLE_SHARED)
 pythonize_bool(LIBCXXABI_ENABLE_THREADS)
 pythonize_bool(LIBCXXABI_ENABLE_EXCEPTIONS)
 pythonize_bool(LIBCXXABI_USE_LLVM_UNWINDER)
-pythonize_bool(LIBCXXABI_HAS_CXA_THREAD_ATEXIT_IMPL)
 set(LIBCXXABI_TARGET_INFO "libcxx.test.target_info.LocalTI" CACHE STRING
     "TargetInfo to use when setting up test environment.")
 set(LIBCXXABI_EXECUTOR "None" CACHE STRING

libcxxabi/test/cxa_thread_atexit_test.pass.cpp

@@ -8,7 +8,6 @@
 //===----------------------------------------------------------------------===//
 
 // REQUIRES: linux
-// REQUIRES: thread_atexit
 
 #include <assert.h>
 #include <cxxabi.h>

libcxxabi/test/libcxxabi/test/config.py

@@ -37,8 +37,6 @@ class Configuration(LibcxxConfiguration):
         super(Configuration, self).configure_features()
         if not self.get_lit_bool('enable_exceptions', True):
             self.config.available_features.add('libcxxabi-no-exceptions')
-        if self.get_lit_bool('thread_atexit', True):
-            self.config.available_features.add('thread_atexit')
 
     def configure_compile_flags(self):
         self.cxx.compile_flags += ['-DLIBCXXABI_NO_TIMER']

libcxxabi/test/lit.site.cfg.in

@@ -13,7 +13,6 @@ config.use_sanitizer            = "@LLVM_USE_SANITIZER@"
 config.enable_32bit             = "@LIBCXXABI_BUILD_32_BITS@"
 config.target_info              = "@LIBCXXABI_TARGET_INFO@"
 config.executor                 = "@LIBCXXABI_EXECUTOR@"
-config.thread_atexit            = "@LIBCXXABI_HAS_CXA_THREAD_ATEXIT_IMPL@"
 config.libcxxabi_shared         = "@LIBCXXABI_ENABLE_SHARED@"
 config.enable_shared            = "@LIBCXX_ENABLE_SHARED@"
 config.enable_exceptions        = "@LIBCXXABI_ENABLE_EXCEPTIONS@"

libcxxabi/test/thread_local_destruction_order.pass.cpp

@@ -0,0 +1,56 @@
+//===-------------- thread_local_destruction_order.pass.cpp ---------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+#include <cassert>
+#include <thread>
+
+int seq = 0;
+
+class OrderChecker {
+public:
+  explicit OrderChecker(int n) : n_{n} { }
+
+  ~OrderChecker() {
+    assert(seq++ == n_);
+  }
+
+private:
+  int n_;
+};
+
+template <int ID>
+class CreatesThreadLocalInDestructor {
+public:
+  ~CreatesThreadLocalInDestructor() {
+    thread_local OrderChecker checker{ID};
+  }
+};
+
+OrderChecker global{7};
+
+void thread_fn() {
+  static OrderChecker fn_static{5};
+  thread_local CreatesThreadLocalInDestructor<2> creates_tl2;
+  thread_local OrderChecker fn_thread_local{1};
+  thread_local CreatesThreadLocalInDestructor<0> creates_tl0;
+}
+
+int main() {
+  static OrderChecker fn_static{6};
+
+  std::thread{thread_fn}.join();
+  assert(seq == 3);
+
+  thread_local OrderChecker fn_thread_local{4};
+  thread_local CreatesThreadLocalInDestructor<3> creates_tl;
+
+  return 0;
+}