- do n = libc.threads_minus_1;
- while (n && a_cas(&libc.threads_minus_1, n, n-1)!=n);
- if (!n) exit(0);
+ /* Block all signals before decrementing the live thread count.
+ * This is important to ensure that dynamically allocated TLS
+ * is not under-allocated/over-committed, and possibly for other
+ * reasons as well. */
+ __block_all_sigs(&set);
+
+ /* Wait to unlock the kill lock, which governs functions like
+ * pthread_kill which target a thread id, until signals have
+ * been blocked. This precludes observation of the thread id
+ * as a live thread (with application code running in it) after
+ * the thread was reported dead by ESRCH being returned. */
+ __unlock(self->killlock);
+
+ /* It's impossible to determine whether this is "the last thread"
+ * until performing the atomic decrement, since multiple threads
+ * could exit at the same time. For the last thread, revert the
+ * decrement and unblock signals to give the atexit handlers and
+ * stdio cleanup code a consistent state. */
+ if (a_fetch_add(&libc.threads_minus_1, -1)==0) {
+ libc.threads_minus_1 = 0;
+ __restore_sigs(&set);
+ exit(0);
+ }