MINOR: fd cache: And the thread_mask with all_threads_mask.

When we choose to insert a fd in either the global or the local fd update list,
and the thread_mask against all_threads_mask before checking if it's tid_bit,
that way, if we run with nbthreads==1, we will always use the local list,
which is cheaper than the global one.
diff --git a/include/proto/fd.h b/include/proto/fd.h
index a4cee32..a3ec5e8 100644
--- a/include/proto/fd.h
+++ b/include/proto/fd.h
@@ -109,7 +109,7 @@
  */
 static inline void updt_fd_polling(const int fd)
 {
-	if (fdtab[fd].thread_mask == tid_bit) {
+	if ((fdtab[fd].thread_mask & all_threads_mask) == tid_bit) {
 		unsigned int oldupdt;
 
 		/* note: we don't have a test-and-set yet in hathreads */