From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH 1/5] Add a global synchronization point for pvclock Date: Mon, 19 Apr 2010 14:13:06 +0300 Message-ID: <4BCC3AC2.8050601@redhat.com> References: <1271356648-5108-1-git-send-email-glommer@redhat.com> <1271356648-5108-2-git-send-email-glommer@redhat.com> <4BCA026D.3070309@redhat.com> <4BCA02D1.2020608@redhat.com> <1271673836.1674.757.camel@laptop> <4BCC34DF.6030702@redhat.com> <1271674575.1674.793.camel@laptop> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Cc: Glauber Costa , kvm@vger.kernel.org, linux-kernel@vger.kernel.org, Jeremy Fitzhardinge , Marcelo Tosatti , Zachary Amsden To: Peter Zijlstra Return-path: In-Reply-To: <1271674575.1674.793.camel@laptop> Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On 04/19/2010 01:56 PM, Peter Zijlstra wrote: > > >>> Right, do bear in mind that the x86 implementation of atomic64_read() is >>> terrifyingly expensive, it is better to not do that read and simply use >>> the result of the cmpxchg. >>> >>> >>> >> atomic64_read() _is_ cmpxchg64b. Are you thinking of some clever >> implementation for smp i386? >> > > No, what I was suggesting was to rewrite that loop no to need the > initial read but use the cmpxchg result of the previous iteration. > > Something like: > > u64 last = 0; > > /* more stuff */ > > do { > if (ret< last) > return last; > last = cmpxchg64(&last_value, last, ret); > } while (last != ret); > > That only has a single cmpxchg8 in there per loop instead of two > (avoiding the atomic64_read() one). > Still have two cmpxchgs in the common case. The first iteration will fail, fetching last_value, the second will work. It will be better when we have contention, though, so it's worthwhile. -- error compiling committee.c: too many arguments to function