Fixes for very early use of the pthread_mutex_* and libthr malloc.

When libthr is statically linked into the binary, order of the
constructors execution is not deterministic.  It is possible for the
application constructor to use pthread_mutex_* functions before the
libthr initialization was done.

Handle it by:
- making thr_malloc.c locking functions operational when curthread is not
  yet set;
- making __thr_malloc_init() idempotent, allowing more than one call to it;
- unconditionally calling __thr_malloc_init() before initializing
  a process-private mutex.

Reported and tested by:	mmel
Sponsored by:	The FreeBSD Foundation
MFC after:	1 week

lib/libthr/thread/thr_malloc.c

@@ -46,6 +46,8 @@ void
 __thr_malloc_init(void)
 {
 
+	if (npagesizes != 0)
+		return;
 	npagesizes = getpagesizes(pagesizes_d, nitems(pagesizes_d));
 	if (npagesizes == -1) {
 		npagesizes = 1;
@@ -59,6 +61,8 @@ static void
 thr_malloc_lock(struct pthread *curthread)
 {
 
+	if (curthread == NULL)
+		return;
 	curthread->locklevel++;
 	_thr_umutex_lock(&thr_malloc_umtx, TID(curthread));
 }
@@ -67,6 +71,8 @@ static void
 thr_malloc_unlock(struct pthread *curthread)
 {
 
+	if (curthread == NULL)
+		return;
 	_thr_umutex_unlock(&thr_malloc_umtx, TID(curthread));
 	curthread->locklevel--;
 	_thr_ast(curthread);

lib/libthr/thread/thr_mutex.c

@@ -390,6 +390,7 @@ __pthread_mutex_init(pthread_mutex_t * __restrict mutex,
 	}
 	if (mutex_attr == NULL ||
 	    (*mutex_attr)->m_pshared == PTHREAD_PROCESS_PRIVATE) {
+		__thr_malloc_init();
 		return (mutex_init(mutex, mutex_attr ? *mutex_attr : NULL,
 		    __thr_calloc));
 	}