Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756486AbZCYQls (ORCPT ); Wed, 25 Mar 2009 12:41:48 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753323AbZCYQlj (ORCPT ); Wed, 25 Mar 2009 12:41:39 -0400 Received: from outbound-sin.frontbridge.com ([207.46.51.80]:12188 "EHLO SG2EHSOBE005.bigfish.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753321AbZCYQli (ORCPT ); Wed, 25 Mar 2009 12:41:38 -0400 X-BigFish: VPS-25(zz1432R98dR1805Mzz1202hzzz2fh6bh62h) X-Spam-TCS-SCL: 1:0 Message-ID: <49CA5EA9.2080106@am.sony.com> Date: Wed, 25 Mar 2009 09:41:13 -0700 From: Tim Bird User-Agent: Thunderbird 2.0.0.14 (X11/20080501) MIME-Version: 1.0 To: Ingo Molnar CC: Russell King - ARM Linux , Frederic Weisbecker , Abhishek Sagar , linux-arm-kernel , linux kernel , Steven Rostedt , Ingo Molnar , =?UTF-8?B?VXdlIEtsZWluZS1Lw7ZuaWc=?= Subject: Re: Anyone working on ftrace function graph support on ARM? References: <49C936CA.8070800@am.sony.com> <20090324213618.GC5975@nowhere> <49C95EAF.7030901@gmail.com> <20090324224857.GE5975@nowhere> <20090325084248.GF4697@n2100.arm.linux.org.uk> <20090325085418.GA2341@elte.hu> In-Reply-To: <20090325085418.GA2341@elte.hu> Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-OriginalArrivalTime: 25 Mar 2009 16:41:15.0044 (UTC) FILETIME=[8374BE40:01C9AD68] X-SEL-encryption-scan: scanned Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1123 Lines: 29 Ingo Molnar wrote: > Unwinding is not realistic or desired for the function tracer - it > runs in every kernel function so performance is paramount. > > So, if i understood you correctly, an OABI_COMPAT and FRAME_POINTERS > dependency has to be added to the ARM HAVE_FUNCTION_GRAPH_TRACER > Kconfig rule. This, unfortunately, is a problem for me. All my ARM projects are now using EABI. If the unwinding looks like it has too much overhead, I'll do some research on the -finstrument-functions (__cyg_profile_func_enter/exit) approach. I'm not sure, however, if it's possible to integrate this with the dynamic tracing mechanisms, though. So something may have to give to get this supported on ARM. -- Tim ============================= Tim Bird Architecture Group Chair, CE Linux Forum Senior Staff Engineer, Sony Corporation of America ============================= -- 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/