[PATCH 03/10] x86/asm: Tweak the comment about wmb() use for IO

From: Borislav Petkov
Date: Tue Jan 26 2016 - 16:15:05 EST

From: "Michael S. Tsirkin" <mst@xxxxxxxxxx>

On x86, we *do* still use the non-nop rmb()/wmb() for IO barriers, but
even that is generally questionable.

Leave them around for historical reasons, unless somebody can point to a
case where they care about the performance. Tweak the comment so people
don't think they are strictly required in all cases.

Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
Cc: Andrey Konovalov <andreyknvl@xxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Davidlohr Bueso <dave@xxxxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: virtualization <virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/1452715911-12067-4-git-send-email-mst@xxxxxxxxxx
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
arch/x86/include/asm/barrier.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index d2aa66a3a4b5..4f95b2affd88 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -6,8 +6,8 @@

* Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
+ *
+ * And yes, this might be required on UP too when we're talking to devices.

#ifdef CONFIG_X86_32