Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752373AbdGLNIe (ORCPT ); Wed, 12 Jul 2017 09:08:34 -0400 Received: from merlin.infradead.org ([205.233.59.134]:33334 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751850AbdGLNId (ORCPT ); Wed, 12 Jul 2017 09:08:33 -0400 Date: Wed, 12 Jul 2017 15:08:26 +0200 From: Peter Zijlstra To: Boqun Feng Cc: Will Deacon , Paul McKenney , linux-kernel@vger.kernel.org, Ingo Molnar , Thomas Gleixner Subject: Re: [RFC][PATCH]: documentation,atomic: Add a new atomic_t document Message-ID: <20170712130826.6qs4fcrwkowe4uoh@hirez.programming.kicks-ass.net> References: <20170609092450.jwmldgtli57ozxgq@hirez.programming.kicks-ass.net> <20170609154442.GB9236@arm.com> <20170609193604.ncw3hhgvewzc3h5u@hirez.programming.kicks-ass.net> <20170611135632.sl72klbeklelupej@tardis> <20170612144929.3wiwtbqopsfpm3qk@hirez.programming.kicks-ass.net> <20170712125347.xz2atyddeilhtdnd@tardis> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20170712125347.xz2atyddeilhtdnd@tardis> User-Agent: NeoMutt/20170609 (1.8.3) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1586 Lines: 38 On Wed, Jul 12, 2017 at 08:53:47PM +0800, Boqun Feng wrote: > On Mon, Jun 12, 2017 at 04:49:29PM +0200, Peter Zijlstra wrote: > [...] > > -Any atomic operation that modifies some state in memory and returns information > > -about the state (old or new) implies an SMP-conditional general memory barrier > > -(smp_mb()) on each side of the actual operation (with the exception of > > -explicit lock operations, described later). These include: > > - > > - xchg(); > > - atomic_xchg(); atomic_long_xchg(); > > - atomic_inc_return(); atomic_long_inc_return(); > > - atomic_dec_return(); atomic_long_dec_return(); > > - atomic_add_return(); atomic_long_add_return(); > > - atomic_sub_return(); atomic_long_sub_return(); > > - atomic_inc_and_test(); atomic_long_inc_and_test(); > > - atomic_dec_and_test(); atomic_long_dec_and_test(); > > - atomic_sub_and_test(); atomic_long_sub_and_test(); > > - atomic_add_negative(); atomic_long_add_negative(); > > - test_and_set_bit(); > > - test_and_clear_bit(); > > - test_and_change_bit(); > > - > > The bit related operations are removed from memory-barriers.txt, I think > we'd better add them in atomic_t.txt? By "them", I mean: > > test_and_{set,clear,change}_bit() as RMW atomic > > {set,clear,change}_bit() as non-RMW atomic > > test_and_set_bit_lock() > clear_bit_unlock() as non-RMW(but barrier-like) atomic I was thinking maybe a separate file, as I was hoping to eventually write a separate file on spinlocks too. I'd like to keep the the new thing purely about the atomic* family of stuff, that's large enough as is.