replace the flockfile backend with a per FILE recursive mutex.

the flockfile implementation in thread/rthread_file.c used an
external lock, and associated it with the relevant FILE * as needed.
this isn't great for a lot of reasons, complexity being the big
one, but the straw that broke the camels back is that it uses a
single spinlock to coordinate all of this, which in turn generates
a lot of sched_yield syscalls.

this avoids all the code complexity and the spinlock by just embedding
a small __rctmx in every FILE.

tested by and ok tb@ jca@
ok claudio@

1 files changed, 7 insertions, 1 deletions

diff --git a/src/lib/libc/include/thread_private.h b/src/lib/libc/include/thread_private.h
index 7e7c716e2a..3e1dbcdf6e 100644
--- a/src/lib/libc/include/thread_private.h
+++ b/src/lib/libc/include/thread_private.h
@@ -1,4 +1,4 @@
-/* $OpenBSD: thread_private.h,v 1.39 2025/07/16 16:22:58 deraadt Exp $ */
+/* $OpenBSD: thread_private.h,v 1.40 2025/08/04 01:44:33 dlg Exp $ */
 
 /* PUBLIC DOMAIN: No Rights Reserved. Marco S Hyman <marc@snafu.org> */
 
@@ -383,6 +383,12 @@ struct __rcmtx {
         unsigned int            depth;
 };
 
+#define __RCMTX_INITIALIZER() {                                         \
+        .owner = NULL,                                                  \
+        .mtx = __CMTX_INITIALIZER(),                                    \
+        .depth = 0,                                                     \
+}
+
 struct pthread_mutex_attr {
         int ma_type;
         int ma_protocol;