Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751783AbbEDPiE (ORCPT ); Mon, 4 May 2015 11:38:04 -0400 Received: from mx1.redhat.com ([209.132.183.28]:58543 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750992AbbEDPiA (ORCPT ); Mon, 4 May 2015 11:38:00 -0400 Message-ID: <55479224.2050509@redhat.com> Date: Mon, 04 May 2015 08:37:08 -0700 From: Richard Henderson User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.6.0 MIME-Version: 1.0 To: Peter Zijlstra , Linus Torvalds CC: Vladimir Makarov , Jakub Jelinek , Ingo Molnar , "H. Peter Anvin" , Thomas Gleixner , Linux Kernel Mailing List , Borislav Petkov Subject: Re: [PATCH] x86: Optimize variable_test_bit() References: <20150501151630.GH5029@twins.programming.kicks-ass.net> <20150501163329.GU1751@tucnak.redhat.com> <5543CDC0.6010206@redhat.com> <20150502123958.GK5029@twins.programming.kicks-ass.net> In-Reply-To: <20150502123958.GK5029@twins.programming.kicks-ass.net> Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2190 Lines: 58 On 05/02/2015 05:39 AM, Peter Zijlstra wrote: > On Fri, May 01, 2015 at 01:49:52PM -0700, Linus Torvalds wrote: >> On Fri, May 1, 2015 at 12:02 PM, Vladimir Makarov wrote: >>> >>> GCC RA is a major reason to prohibit output operands for asm goto. >> >> Hmm.. Thinking some more about it, I think that what would actually >> work really well at least for the kernel is: >> >> (a) allow *memory* operands (ie "=m") as outputs and having them be >> meaningful even at any output labels (obviously with the caveat that >> the asm instructions that write to memory would have to happen before >> the branch ;) >> >> This covers the somewhat common case of having magic instructions that >> result in conditions that can't be tested at a C level. Things like >> "bit clear and test" on x86 (with or without the lock) . > > Would not something like: > > static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) > { > bool oldbit; > > asm volatile ("btr %2, %1" > : "CF" (oldbit), "+m" (*addr) > : "Ir" (nr)); > > return oldbit; > } > > Be the far better solution for this? Bug 59615 comment 7 states that > they actually modeled the flags in the .md file, so the above should be > possible to implement. > > Now GCC can decide to use "sbb %0, %0" to convert CF into a register > value or use "jnc" / "jc" for branches, depending on what > __test_and_clear_bit() was used for. > > We don't have to (ab)use asm goto for these things anymore; furthermore > I think the above will naturally work with our __builtin_expect() hints, > whereas the asm goto stuff has a hard time with that (afaik). > > That's not to say output operants for asm goto would not still be useful > for other things (like your EXTABLE example). > I agree that being able to model flags outputs, and thus minimize the amount of code actually within the asm, is superior to the complexity of asm goto. r~ -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/