From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965259Ab1JFRxg (ORCPT ); Thu, 6 Oct 2011 13:53:36 -0400 Received: from claw.goop.org ([74.207.240.146]:33771 "EHLO claw.goop.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S965181Ab1JFRxf (ORCPT ); Thu, 6 Oct 2011 13:53:35 -0400 Message-ID: <4E8DEB19.1050509@goop.org> Date: Thu, 06 Oct 2011 10:53:29 -0700 From: Jeremy Fitzhardinge User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:7.0.1) Gecko/20110930 Thunderbird/7.0.1 MIME-Version: 1.0 To: "H. Peter Anvin" CC: Jason Baron , Steven Rostedt , "David S. Miller" , David Daney , Michael Ellerman , Jan Glauber , the arch/x86 maintainers , Xen Devel , Linux Kernel Mailing List , Jeremy Fitzhardinge , peterz@infradead.org Subject: Re: [PATCH RFC V2 3/5] jump_label: if a key has already been initialized, don't nop it out References: <477dead9647029012f93c651f2892ed0e86b89e7.1317506051.git.jeremy.fitzhardinge@citrix.com> <20111003150205.GB2462@redhat.com> <4E89E28C.7010700@goop.org> <20111004141011.GA2520@redhat.com> <4E8B3489.60902@zytor.com> <4E8CF348.4080405@goop.org> <4E8CF385.2080804@zytor.com> In-Reply-To: <4E8CF385.2080804@zytor.com> X-Enigmail-Version: 1.3.2 Content-Type: multipart/mixed; boundary="------------060407060807030203080909" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org This is a multi-part message in MIME format. --------------060407060807030203080909 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit On 10/05/2011 05:17 PM, H. Peter Anvin wrote: > On 10/05/2011 05:16 PM, Jeremy Fitzhardinge wrote: >> On 10/04/2011 09:30 AM, H. Peter Anvin wrote: >>> On 10/04/2011 07:10 AM, Jason Baron wrote: >>>> 1) The jmp +0, is a 'safe' no-op that I know is going to initially >>>> boot for all x86. I'm not sure if there is a 5-byte nop that works on >>>> all x86 variants - but by using jmp +0, we make it much easier to debug >>>> cases where we may be using broken no-ops. >>>> >>> There are *plenty*. jmp+0 is about as pessimal as you can get. >> As an aside, do you know if a 2-byte unconditional jmp is any more >> efficient than 5-byte, aside from just being a smaller instruction and >> taking less icache? >> > I don't know for sure, no. I probably depends on the CPU. Looks like jmp2 is about 5% faster than jmp5 on Sandybridge with this benchmark. But insignificant difference on Nehalem. J --------------060407060807030203080909 Content-Type: text/x-csrc; name="jmp2.c" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="jmp2.c" #include struct { unsigned char flag; unsigned char val; } l; #define JMP2 asm volatile ("jmp 1f; .byte 0x0f,0x1f,0x00; 1: "); #define JMPJMP2 JMP2 JMP2 #define JMPJMPJMP2 JMPJMP2 JMPJMP2 #define JMPJMPJMP2 JMPJMP2 JMPJMP2 #define JMPJMPJMPJMP2 JMPJMPJMP2 JMPJMPJMP2 #define JMPJMPJMPJMPJMP2 JMPJMPJMPJMP2 JMPJMPJMPJMP2 #define JMPJMPJMPJMPJMPJMP2 JMPJMPJMPJMPJMP2 JMPJMPJMPJMPJMP2 int main(int argc, char **argv) { int i; for (i = 0; i < 100000000; i++) { JMPJMPJMPJMPJMPJMP2; asm volatile("" : : : "memory"); } return 0; } --------------060407060807030203080909 Content-Type: text/x-csrc; name="jmp5.c" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="jmp5.c" #include struct { unsigned char flag; unsigned char val; } l; #define JMP5 asm volatile (".byte 0xe9; .long 0"); #define JMPJMP5 JMP5 JMP5 #define JMPJMPJMP5 JMPJMP5 JMPJMP5 #define JMPJMPJMP5 JMPJMP5 JMPJMP5 #define JMPJMPJMPJMP5 JMPJMPJMP5 JMPJMPJMP5 #define JMPJMPJMPJMPJMP5 JMPJMPJMPJMP5 JMPJMPJMPJMP5 #define JMPJMPJMPJMPJMPJMP5 JMPJMPJMPJMPJMP5 JMPJMPJMPJMPJMP5 int main(int argc, char **argv) { int i; for (i = 0; i < 100000000; i++) { JMPJMPJMPJMPJMPJMP5; asm volatile("" : : : "memory"); } return 0; } --------------060407060807030203080909--