[src/trunk]: src/sys/arch/mips/include mips: Redefine BDSYNC as sync on Octeo...

[riastradh <riastradh%NetBSD.org@localhost>]

details:   https://anonhg.NetBSD.org/src/rev/1b391c129697
branches:  trunk
changeset: 362456:1b391c129697
user:      riastradh <riastradh%NetBSD.org@localhost>
date:      Sun Feb 27 19:22:12 2022 +0000

description:
mips: Redefine BDSYNC as sync on Octeon, not syncw.

BDSYNC is used for membar_sync, which is supposed to be a full
sequential consistency barrier, which is not provided by syncw, so
this is necessary for correctness.

BDSYNC is not used for anything else, so this can't hurt performance,
except where it was necessary for correctness anyway or where the
semantic choice of membar_sync was too strong anyway.

diffstat:

 sys/arch/mips/include/asm.h |  4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diffs (18 lines):

diff -r 539462a4a3ea -r 1b391c129697 sys/arch/mips/include/asm.h
--- a/sys/arch/mips/include/asm.h       Sun Feb 27 19:22:02 2022 +0000
+++ b/sys/arch/mips/include/asm.h       Sun Feb 27 19:22:12 2022 +0000
@@ -1,4 +1,4 @@
-/*     $NetBSD: asm.h,v 1.67 2022/02/27 19:22:02 riastradh Exp $       */
+/*     $NetBSD: asm.h,v 1.68 2022/02/27 19:22:12 riastradh Exp $       */
 
 /*
  * Copyright (c) 1992, 1993
@@ -574,7 +574,7 @@
 #if defined(__OCTEON__)
                                /* early cnMIPS have erratum which means 2 */
 #define        LLSCSYNC        sync 4; sync 4
-#define        BDSYNC          sync 4          /* sync 4 == syncw - sync all writes */
+#define        BDSYNC          sync
 #define        BDSYNC_ACQ      sync
 #define        SYNC_ACQ        sync
 #define        SYNC_REL        sync