From mboxrd@z Thu Jan 1 00:00:00 1970 From: Namhyung Kim Subject: Re: [PATCH] perf report: fix off-by-one for non-activation frames Date: Tue, 16 May 2017 10:57:53 +0900 Message-ID: <20170516015753.GB4885@sejong> References: <20170515150444.6841-1-milian.wolff@kdab.com> <12254594.nNfBy6txoy@milian-kdab2> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Return-path: Received: from LGEAMRELO12.lge.com ([156.147.23.52]:47256 "EHLO lgeamrelo12.lge.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751228AbdEPB54 (ORCPT ); Mon, 15 May 2017 21:57:56 -0400 Content-Disposition: inline In-Reply-To: <12254594.nNfBy6txoy@milian-kdab2> Sender: linux-perf-users-owner@vger.kernel.org List-ID: To: Milian Wolff Cc: 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 On Mon, May 15, 2017 at 05:13:06PM +0200, Milian Wolff wrote: > On Monday, May 15, 2017 5:04:44 PM CEST Milian Wolff wrote: > > As the documentation for dwfl_frame_pc says, frames that > > are no activation frames need to have their program counter > > decremented by one to properly find the function of the caller. > > Note that this leaves the perf build against libunwind in the current, broken > state. I do not know how to detect the activation property there. Does anyone > else? See elfutils source code for what it is doing: > > https://sourceware.org/git/?p=elfutils.git;a=blob;f=libdwfl/ > dwfl_frame_pc.c;h=296c815b9c73f42d79ac1778d2a0c420b89ee4eb;hb=HEAD It seems that you can use unw_is_signal_frame(). Thanks, Namhyung