From mboxrd@z Thu Jan 1 00:00:00 1970 From: Willy Tarreau Subject: Re: [PATCH stable 4.9 1/8] x86: bpf_jit: small optimization in emit_bpf_tail_call() Date: Mon, 29 Jan 2018 07:39:19 +0100 Message-ID: <20180129063919.GA20230@1wt.eu> References: <0f909080f2ef055783fc7b394e8111e0df3c4971.1517190206.git.daniel@iogearbox.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: ast@kernel.org, netdev@vger.kernel.org, Eric Dumazet , "David S . Miller" To: Daniel Borkmann Return-path: Received: from wtarreau.pck.nerim.net ([62.212.114.60]:40190 "EHLO 1wt.eu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751032AbeA2Gjk (ORCPT ); Mon, 29 Jan 2018 01:39:40 -0500 Content-Disposition: inline In-Reply-To: <0f909080f2ef055783fc7b394e8111e0df3c4971.1517190206.git.daniel@iogearbox.net> Sender: netdev-owner@vger.kernel.org List-ID: Hi, [ replaced stable@ and greg@ by netdev@ as my question below is not relevant to stable ] On Mon, Jan 29, 2018 at 02:48:54AM +0100, Daniel Borkmann wrote: > From: Eric Dumazet > > [ upstream commit 84ccac6e7854ebbfb56d2fc6d5bef9be49bb304c ] > > Saves 4 bytes replacing following instructions : > > lea rax, [rsi + rdx * 8 + offsetof(...)] > mov rax, qword ptr [rax] > cmp rax, 0 > > by : > > mov rax, [rsi + rdx * 8 + offsetof(...)] > test rax, rax I've just noticed this on stable@. If these 4 bytes matter, why not use cmpq with an immediate value instead, which saves 2 extra bytes ? : - the mov above is 11 bytes total : 0: 48 8b 84 d6 78 56 34 mov 0x12345678(%rsi,%rdx,8),%rax 7: 12 8: 48 85 c0 test %rax,%rax - the equivalent cmp is only 9 bytes : 0: 48 83 bc d6 78 56 34 cmpq $0x0,0x12345678(%rsi,%rdx,8) 7: 12 00 And as a bonus, it doesn't even clobber rax. Just my two cents, Willy