avoid using pthread cleanup push/pop in stdio when not needed

unfortunately in dynamic-linked programs, these macros cause
pthread_self to be initialized, which costs a couple syscalls, and
(much worse) would necessarily fail, crash, and burn on ancient (2.4
and earlier) kernels where setting up a thread pointer does not work.

i'd like to do this in a more generic way that avoids all use of
cleanup push/pop before pthread_self has been successfully called and
avoids ugly if/else constructs like the one in this commit, but for
now, this will suffice.

src/stdio/__stdio_read.c

@@ -15,9 +15,13 @@ size_t __stdio_read(FILE *f, unsigned char *buf, size_t len)
 	};
 	ssize_t cnt;
 
-	pthread_cleanup_push(cleanup, f);
-	cnt = syscall_cp(SYS_readv, f->fd, iov, 2);
-	pthread_cleanup_pop(0);
+	if (libc.main_thread) {
+		pthread_cleanup_push(cleanup, f);
+		cnt = syscall_cp(SYS_readv, f->fd, iov, 2);
+		pthread_cleanup_pop(0);
+	} else {
+		cnt = syscall(SYS_readv, f->fd, iov, 2);
+	}
 	if (cnt <= 0) {
 		f->flags |= F_EOF ^ ((F_ERR^F_EOF) & cnt);
 		f->rpos = f->rend = 0;

src/stdio/__stdio_write.c

@@ -18,9 +18,13 @@ size_t __stdio_write(FILE *f, const unsigned char *buf, size_t len)
 	int iovcnt = 2;
 	ssize_t cnt;
 	for (;;) {
-		pthread_cleanup_push(cleanup, f);
-		cnt = syscall_cp(SYS_writev, f->fd, iov, iovcnt);
-		pthread_cleanup_pop(0);
+		if (libc.main_thread) {
+			pthread_cleanup_push(cleanup, f);
+			cnt = syscall_cp(SYS_writev, f->fd, iov, iovcnt);
+			pthread_cleanup_pop(0);
+		} else {
+			cnt = syscall(SYS_writev, f->fd, iov, iovcnt);
+		}
 		if (cnt == rem) {
 			f->wend = f->buf + f->buf_size;
 			f->wpos = f->wbase = f->buf;