restore lock-skipping for processes that return to single-threaded state

[musl] / src / thread / pthread_create.c

diff --git a/src/thread/pthread_create.c b/src/thread/pthread_create.c
index 5d00d76..6bdfb44 100644 (file)
--- a/src/thread/pthread_create.c
+++ b/src/thread/pthread_create.c
@@ -90,14 +90,7 @@ _Noreturn void __pthread_exit(void *result)
                exit(0);
        }
 
-       /* At this point we are committed to thread termination. Unlink
-        * the thread from the list. This change will not be visible
-        * until the lock is released, which only happens after SYS_exit
-        * has been called, via the exit futex address pointing at the lock. */
-       libc.threads_minus_1--;
-       self->next->prev = self->prev;
-       self->prev->next = self->next;
-       self->prev = self->next = self;
+       /* At this point we are committed to thread termination. */
 
        /* Process robust list in userspace to handle non-pshared mutexes
         * and the detached thread case where the robust list head will
@@ -121,6 +114,16 @@ _Noreturn void __pthread_exit(void *result)
        __do_orphaned_stdio_locks();
        __dl_thread_cleanup();
 
+       /* Last, unlink thread from the list. This change will not be visible
+        * until the lock is released, which only happens after SYS_exit
+        * has been called, via the exit futex address pointing at the lock.
+        * This needs to happen after any possible calls to LOCK() that might
+        * skip locking if process appears single-threaded. */
+       if (!--libc.threads_minus_1) libc.need_locks = -1;
+       self->next->prev = self->prev;
+       self->prev->next = self->next;
+       self->prev = self->next = self;
+
        /* This atomic potentially competes with a concurrent pthread_detach
         * call; the loser is responsible for freeing thread resources. */
        int state = a_cas(&self->detach_state, DT_JOINABLE, DT_EXITING);
@@ -185,7 +188,7 @@ static int start(void *p)
                        __wait(&args->control, 0, 2, 1);
                if (args->control) {
                        __syscall(SYS_set_tid_address, &args->control);
-                       return 0;
+                       for (;;) __syscall(SYS_exit, 0);
                }
        }
        __syscall(SYS_rt_sigprocmask, SIG_SETMASK, &args->sig_mask, 0, _NSIG/8);
@@ -336,7 +339,7 @@ int __pthread_create(pthread_t *restrict res, const pthread_attr_t *restrict att
                ~(1UL<<((SIGCANCEL-1)%(8*sizeof(long))));
 
        __tl_lock();
-       libc.threads_minus_1++;
+       if (!libc.threads_minus_1++) libc.need_locks = 1;
        ret = __clone((c11 ? start_c11 : start), stack, flags, args, &new->tid, TP_ADJ(new), &__thread_list_lock);
 
        /* All clone failures translate to EAGAIN. If explicit scheduling
@@ -360,7 +363,7 @@ int __pthread_create(pthread_t *restrict res, const pthread_attr_t *restrict att
                new->next->prev = new;
                new->prev->next = new;
        } else {
-               libc.threads_minus_1--;
+               if (!--libc.threads_minus_1) libc.need_locks = 0;
        }
        __tl_unlock();
        __restore_sigs(&set);