Mark sched_yield(2) as NOLOCK.

All the fields accessed in this syscall are protected by the SCHED_LOCK()
so it isn't necessary to wait for another CPU to release the KERNEL_LOCK()
before that.

ok claudio@

diff --git a/sys/kern/syscalls.master b/sys/kern/syscalls.master
index 59f4a97..56baf29 100644 (file)
--- a/sys/kern/syscalls.master
+++ b/sys/kern/syscalls.master
@@ -1,4 +1,4 @@
-;      $OpenBSD: syscalls.master,v 1.235 2022/11/08 11:05:57 mpi Exp $
+;      $OpenBSD: syscalls.master,v 1.236 2022/11/09 10:26:28 mpi Exp $
 ;      $NetBSD: syscalls.master,v 1.32 1996/04/23 10:24:21 mycroft Exp $
 
 ;      @(#)syscalls.master     8.2 (Berkeley) 1/13/94
@@ -531,7 +531,7 @@
 #else
 297    UNIMPL
 #endif
-298    STD             { int sys_sched_yield(void); }
+298    STD NOLOCK      { int sys_sched_yield(void); }
 299    STD NOLOCK      { pid_t sys_getthrid(void); }
 300    OBSOL           t32___thrsleep
 301    STD NOLOCK      { int sys___thrwakeup(const volatile void *ident, \