Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752540AbZKSQpm (ORCPT ); Thu, 19 Nov 2009 11:45:42 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751480AbZKSQpl (ORCPT ); Thu, 19 Nov 2009 11:45:41 -0500 Received: from www.tglx.de ([62.245.132.106]:53472 "EHLO www.tglx.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751103AbZKSQpk (ORCPT ); Thu, 19 Nov 2009 11:45:40 -0500 Date: Thu, 19 Nov 2009 17:43:45 +0100 (CET) From: Thomas Gleixner To: Andrew Haley cc: Ingo Molnar , "H. Peter Anvin" , LKML , Andrew Morton , Heiko Carstens , feng.tang@intel.com, Fr??d??ric Weisbecker , Steven Rostedt , Peter Zijlstra , jakub@redhat.com, gcc@gcc.gnu.org Subject: Re: BUG: GCC-4.4.x changes the function frame on some functions In-Reply-To: <4B056FAD.2080500@redhat.com> Message-ID: References:

<20091119072040.GA23579@elte.hu> <4B0567E0.5080803@redhat.com> <4B056FAD.2080500@redhat.com> User-Agent: Alpine 2.00 (LFD 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4637 Lines: 101 On Thu, 19 Nov 2009, Andrew Haley wrote: > Thomas Gleixner wrote: > > On Thu, 19 Nov 2009, Andrew Haley wrote: > >> Thomas Gleixner wrote: > >>> There is no real obvious reason why the edi magic needs to be done > >>> _before_ > >>> > >>> push %ebp > >>> mov %esp,%ebp > >> Sure there is: unless you do the adjustment first %ebp won't be 16-aligned. > > > > And why is this not done in 99% of the functions in the kernel, just > > in this one and some random others ? > > If I could see the function I might be able to tell you. It's either a > performance enhancement, something to do with SSE, or it's a bug. kernel/time/timer_stats.c timer_stats_update_stats() Here is the disassembly: 8107ad50 : 8107ad50: 57 push %edi 8107ad51: 8d 7c 24 08 lea 0x8(%esp),%edi 8107ad55: 83 e4 f0 and $0xfffffff0,%esp 8107ad58: ff 77 fc pushl -0x4(%edi) 8107ad5b: 55 push %ebp 8107ad5c: 89 e5 mov %esp,%ebp 8107ad5e: 57 push %edi 8107ad5f: 56 push %esi 8107ad60: 53 push %ebx 8107ad61: 83 ec 6c sub $0x6c,%esp 8107ad64: e8 47 92 f8 ff call 81003fb0 8107ad69: 8b 77 04 mov 0x4(%edi),%esi 8107ad6c: 89 75 a4 mov %esi,-0x5c(%ebp) 8107ad6f: 65 8b 35 14 00 00 00 mov %gs:0x14,%esi 8107ad76: 89 75 e4 mov %esi,-0x1c(%ebp) 8107ad79: 31 f6 xor %esi,%esi 8107ad7b: 8b 35 60 5a cd 81 mov 0x81cd5a60,%esi 8107ad81: 8b 1f mov (%edi),%ebx 8107ad83: 85 f6 test %esi,%esi 8107ad85: 8b 7f 08 mov 0x8(%edi),%edi 8107ad88: 75 18 jne 8107ada2 8107ad8a: 8b 45 e4 mov -0x1c(%ebp),%eax 8107ad8d: 65 33 05 14 00 00 00 xor %gs:0x14,%eax 8107ad94: 75 53 jne 8107ade9 8107ad96: 83 c4 6c add $0x6c,%esp 8107ad99: 5b pop %ebx 8107ad9a: 5e pop %esi 8107ad9b: 5f pop %edi 8107ad9c: 5d pop %ebp 8107ad9d: 8d 67 f8 lea -0x8(%edi),%esp 8107ada0: 5f pop %edi 8107ada1: c3 ret 8107ada2: be 00 7a d6 81 mov $0x81d67a00,%esi 8107ada7: 89 45 ac mov %eax,-0x54(%ebp) 8107adaa: 89 75 a0 mov %esi,-0x60(%ebp) 8107adad: 89 5d b4 mov %ebx,-0x4c(%ebp) 8107adb0: 64 8b 35 78 6a d6 81 mov %fs:0x81d66a78,%esi 8107adb7: 8b 34 b5 20 50 cd 81 mov -0x7e32afe0(,%esi,4),%esi 8107adbe: 89 4d b0 mov %ecx,-0x50(%ebp) 8107adc1: 01 75 a0 add %esi,-0x60(%ebp) 8107adc4: 89 55 b8 mov %edx,-0x48(%ebp) 8107adc7: 8b 45 a0 mov -0x60(%ebp),%eax 8107adca: 89 7d c0 mov %edi,-0x40(%ebp) 8107adcd: e8 de f7 76 00 call 817ea5b0 <_spin_lock_irqsave> 8107add2: 83 3d 60 5a cd 81 00 cmpl $0x0,0x81cd5a60 8107add9: 89 c3 mov %eax,%ebx 8107addb: 75 11 jne 8107adee 8107addd: 89 da mov %ebx,%edx 8107addf: 8b 45 a0 mov -0x60(%ebp),%eax 8107ade2: e8 79 fc 76 00 call 817eaa60 <_spin_unlock_irqrestore> 8107ade7: eb a1 jmp 8107ad8a 8107ade9: e8 52 e4 fc ff call 81049240 <__stack_chk_fail> 8107adee: 8d 45 a8 lea -0x58(%ebp),%eax 8107adf1: 8b 55 a4 mov -0x5c(%ebp),%edx 8107adf4: e8 f7 fd ff ff call 8107abf0 8107adf9: 85 c0 test %eax,%eax 8107adfb: 74 05 je 8107ae02 8107adfd: ff 40 14 incl 0x14(%eax) 8107ae00: eb db jmp 8107addd 8107ae02: f0 ff 05 00 67 fd 81 lock incl 0x81fd6700 8107ae09: eb d2 jmp 8107addd 8107ae0b: 90 nop 8107ae0c: 90 nop 8107ae0d: 90 nop 8107ae0e: 90 nop 8107ae0f: 90 nop There is a dozen more of those. Thanks, tglx -- 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/