From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933656AbcA0PKv (ORCPT ); Wed, 27 Jan 2016 10:10:51 -0500 Received: from mx1.redhat.com ([209.132.183.28]:41822 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932677AbcA0PKp (ORCPT ); Wed, 27 Jan 2016 10:10:45 -0500 Date: Wed, 27 Jan 2016 17:10:39 +0200 From: "Michael S. Tsirkin" To: linux-kernel@vger.kernel.org, Linus Torvalds Cc: Davidlohr Bueso , Peter Zijlstra , Ingo Molnar , Thomas Gleixner , "Paul E. McKenney" , the arch/x86 maintainers , Davidlohr Bueso , "H. Peter Anvin" , virtualization , Borislav Petkov , Andy Lutomirski , Ingo Molnar , Andy Lutomirski , Andrey Konovalov , Borislav Petkov Subject: [PATCH v4 5/5] x86: drop mfence in favor of lock+addl Message-ID: <1453904765-11073-6-git-send-email-mst@redhat.com> References: <1453904765-11073-1-git-send-email-mst@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1453904765-11073-1-git-send-email-mst@redhat.com> X-Mutt-Fcc: =sent Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org mfence appears to be way slower than a locked instruction - let's use lock+add unconditionally, as we always did on old 32-bit. Just poking at SP would be the most natural, but if we then read the value from SP, we get a false dependency which will slow us down. This was noted in this article: http://shipilev.net/blog/2014/on-the-fence-with-dependencies/ And is easy to reproduce by sticking a barrier in a small non-inline function. So let's use a negative offset - which avoids this problem since we build with the red zone disabled. Unfortunately there's some code that wants to order clflush instructions using mb(), so we can't replace that - but smp_mb should be safe to replace. Update mb/rmb/wmb on 32 bit to use the negative offset, too, for consistency. Suggested-by: Andy Lutomirski Signed-off-by: Michael S. Tsirkin --- arch/x86/include/asm/barrier.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index bfb28ca..7ab9581 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -11,11 +11,11 @@ */ #ifdef CONFIG_X86_32 -#define mb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "mfence", \ +#define mb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "mfence", \ X86_FEATURE_XMM2) ::: "memory", "cc") -#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "lfence", \ +#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "lfence", \ X86_FEATURE_XMM2) ::: "memory", "cc") -#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "sfence", \ +#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "sfence", \ X86_FEATURE_XMM2) ::: "memory", "cc") #else #define mb() asm volatile("mfence":::"memory") @@ -30,7 +30,7 @@ #endif #define dma_wmb() barrier() -#define __smp_mb() mb() +#define __smp_mb() asm volatile("lock; addl $0,-4(%%esp)" ::: "memory", "cc") #define __smp_rmb() dma_rmb() #define __smp_wmb() barrier() #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) -- MST