From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: [PATCH v2] perf report: distinguish between inliners in the same function Date: Fri, 12 May 2017 07:55:13 -0700 Message-ID: <87a86igm5q.fsf@firstfloor.org> References: <20170503213536.13905-1-milian.wolff@kdab.com> <20170510055352.GA2667@sejong> <1673560.Uk8cHjlLU8@agathebauer> Mime-Version: 1.0 Content-Type: text/plain Return-path: Received: from mga05.intel.com ([192.55.52.43]:23079 "EHLO mga05.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932315AbdELOzP (ORCPT ); Fri, 12 May 2017 10:55:15 -0400 In-Reply-To: <1673560.Uk8cHjlLU8@agathebauer> (Milian Wolff's message of "Fri, 12 May 2017 12:37:01 +0200") Sender: linux-perf-users-owner@vger.kernel.org List-ID: To: Milian Wolff Cc: Namhyung Kim , linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org, Arnaldo Carvalho de Melo , David Ahern , Peter Zijlstra , Yao Jin , kernel-team@lge.com Milian Wolff writes: > > I think I'm missing something, but isn't this what this function provides? The > function above is now being used by the match_chain_inliner function below. > > Ah, or do you mean for code such as this: > > ~~~~~ > inline_func_1(); inline_func_2(); This could be handled by looking at columns or discriminators too (which some compilers generate in dwarf). srcline.c would need to be changed to also call bfd_get_nearest_discriminator() and pass that extra information everywhere. -Andi