From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-3.8 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, MAILING_LIST_MULTI,SIGNED_OFF_BY,SPF_PASS,URIBL_BLOCKED autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0FCCBC46475 for ; Tue, 23 Oct 2018 19:57:24 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id B001320671 for ; Tue, 23 Oct 2018 19:57:23 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org B001320671 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728403AbeJXEWN convert rfc822-to-8bit (ORCPT ); Wed, 24 Oct 2018 00:22:13 -0400 Received: from mga18.intel.com ([134.134.136.126]:18897 "EHLO mga18.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1725740AbeJXEWM (ORCPT ); Wed, 24 Oct 2018 00:22:12 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by orsmga106.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 23 Oct 2018 12:57:20 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.54,417,1534834800"; d="scan'208";a="97925632" Received: from irsmsx109.ger.corp.intel.com ([163.33.3.23]) by fmsmga002.fm.intel.com with ESMTP; 23 Oct 2018 12:57:18 -0700 Received: from irsmsx106.ger.corp.intel.com ([169.254.8.45]) by IRSMSX109.ger.corp.intel.com ([169.254.13.183]) with mapi id 14.03.0319.002; Tue, 23 Oct 2018 20:57:17 +0100 From: "Hunter, Adrian" To: Arnaldo Carvalho de Melo CC: Jiri Olsa , Andi Kleen , "linux-kernel@vger.kernel.org" Subject: RE: [PATCH V2 17/19] perf scripts python: exported-sql-viewer.py: Add All branches report Thread-Topic: [PATCH V2 17/19] perf scripts python: exported-sql-viewer.py: Add All branches report Thread-Index: AQHUaqaeWJRZYosv3UW89nQIvhP4TKUtEc0AgAATeyCAAAIdgIAAFexw Date: Tue, 23 Oct 2018 19:57:17 +0000 Message-ID: <363DA0ED52042842948283D2FC38E4649C2B8AA7@IRSMSX106.ger.corp.intel.com> References: <20181001062853.28285-18-adrian.hunter@intel.com> <20181023075949.18920-1-adrian.hunter@intel.com> <20181023181218.GB6114@kernel.org> <363DA0ED52042842948283D2FC38E4649C2B8A4D@IRSMSX106.ger.corp.intel.com> <20181023192935.GD6114@kernel.org> In-Reply-To: <20181023192935.GD6114@kernel.org> Accept-Language: en-NZ, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: dlp-product: dlpe-windows dlp-version: 11.0.400.15 dlp-reaction: no-action x-ctpclassification: CTP_NT x-titus-metadata-40: eyJDYXRlZ29yeUxhYmVscyI6IiIsIk1ldGFkYXRhIjp7Im5zIjoiaHR0cDpcL1wvd3d3LnRpdHVzLmNvbVwvbnNcL0ludGVsMyIsImlkIjoiMmU5NTlhMjQtZTBhNC00ZGFjLTgwOTYtNzJjYzg2YzI0MTIyIiwicHJvcHMiOlt7Im4iOiJDVFBDbGFzc2lmaWNhdGlvbiIsInZhbHMiOlt7InZhbHVlIjoiQ1RQX05UIn1dfV19LCJTdWJqZWN0TGFiZWxzIjpbXSwiVE1DVmVyc2lvbiI6IjE3LjEwLjE4MDQuNDkiLCJUcnVzdGVkTGFiZWxIYXNoIjoic0Y1VDNOUHQzcEpxMXB4K0RTdXk0OEp3WTRYY2Y2Y3BQTDVuT2U4ckVZUkNnQ0h1eW54UjlMNEZmSDltNTM2aCJ9 x-originating-ip: [163.33.239.180] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 8BIT MIME-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > -----Original Message----- > From: Arnaldo Carvalho de Melo [mailto:acme@kernel.org] > Sent: Tuesday, October 23, 2018 10:30 PM > To: Hunter, Adrian > Cc: Jiri Olsa ; Andi Kleen ; linux- > kernel@vger.kernel.org > Subject: Re: [PATCH V2 17/19] perf scripts python: exported-sql-viewer.py: > Add All branches report > > Em Tue, Oct 23, 2018 at 06:41:17PM +0000, Hunter, Adrian escreveu: > > > -----Original Message----- > > > From: Arnaldo Carvalho de Melo [mailto:acme@kernel.org] > > > Sent: Tuesday, October 23, 2018 9:12 PM > > > To: Hunter, Adrian > > > Cc: Jiri Olsa ; Andi Kleen ; > > > linux- kernel@vger.kernel.org > > > Subject: Re: [PATCH V2 17/19] perf scripts python: exported-sql- > viewer.py: > > > Add All branches report > > > > > > Em Tue, Oct 23, 2018 at 10:59:49AM +0300, Adrian Hunter escreveu: > > > > Add a report to display branches in a similar fashion to perf script. > > > > The main purpose of this report is to display disassembly, > > > > however, presently, the only supported disassembler is Intel XED, > > > > and additionally the object code must be present in perf build ID cache. > > > > > > > > To use Intel XED, libxed.so must be present. To build and install > > > > libxed.so: > > > > git clone https://github.com/intelxed/mbuild.git mbuild > > > > git clone https://github.com/intelxed/xed > > > > cd xed > > > > ./mfile.py --share > > > > sudo ./mfile.py --prefix=/usr/local install > > > > sudo ldconfig > > > > > > > > Signed-off-by: Adrian Hunter > > > > --- > > > > > > > > > > > > Changes in V2: > > > > > > > > Fix branch report not appearing for kernel-only or user-only tracing: > > > > Find branch events named like "branches:k" or "branches:u" as > > > > well > > > as > > > > just plain "branches", by splitting the name at the colon. i.e. > > > > event = event.split(":")[0] > > > > > > So, I followed the instructions then ended up with: > > > > > > [acme@seventh perf]$ find /usr/local -name "*xed*" | head > > > /usr/local/lib/libxed.so /usr/local/lib/libxed.a > > > /usr/local/lib/libxed-ild.so /usr/local/lib/libxed-ild.a > > > /usr/local/include/xed /usr/local/include/xed/xed- syntax-enum.h > > > /usr/local/include/xed/xed-attributes.h > > > /usr/local/include/xed/xed-build-defines.h > > > /usr/local/include/xed/xed-cpuid-rec.h > > > /usr/local/include/xed/xed-flags.h > > > [acme@seventh perf]$ > > > > > > Ran ldconfig as root, etc: > > > > > > [acme@seventh perf]$ ldconfig -v -N | grep xed What about: ldconfig -p | grep xed > > > ldconfig: Can't stat /libx32: No such file or directory > > > ldconfig: Path `/usr/lib' given more than once > > > ldconfig: Path `/usr/lib64' given more than once > > > ldconfig: Can't stat /usr/libx32: No such file or directory > > > [acme@seventh perf]$ > > > > > > [acme@seventh perf]$ file /usr/local/lib/libxed.so > > > /usr/local/lib/libxed.so: ELF 64-bit LSB shared object, x86-64, > > > version 1 (SYSV), dynamically linked, > > > BuildID[sha1]=09cf45310a731f727b4575582a638052b8f3e3bb, not > stripped > > > [acme@seventh perf]$ file /usr/local/lib/libxed-ild.so > > > /usr/local/lib/libxed-ild.so: ELF 64-bit LSB shared object, x86-64, > > > version 1 (SYSV), dynamically linked, > > > BuildID[sha1]=a5601603e305bb7b7f8edc7da0e78acbc9b63eba, not > stripped > > > [acme@seventh perf]$ > > > > > > Tried with: > > > > > > export LD_LIBRARY_PATH=/usr/local/lib/ > > > > > > But so far couldn't get it to show the disassembly. > > > > > > The "All Branches" is there, wasn't in v1 of this patch. > > > > > > Ideas? > > > > The "All Branches" report is a 2-level tree, and the disassembly > > displays when the next level of the tree is opened i.e. click the arrow at the > start of the line. > > Right, I pressed on those arrows, nothing appeared, do you have any hotkey > to expand them all at once? No there isn't, but it would take quite a while because it doesn't disassemble until it is expanded. > > > Have you tried both kernel and user space? > > [root@seventh perf]# perf evlist -v > intel_pt//u: type: 8, size: 112, config: 0x300e601, { sample_period, > sample_freq }: 1, sample_type: IP|TID|TIME|CPU|IDENTIFIER, read_format: > ID, disabled: 1, inherit: 1, exclude_kernel: 1, exclude_hv: 1, sample_id_all: 1 > dummy:u: type: 1, size: 112, config: 0x9, { sample_period, sample_freq }: 1, > sample_type: IP|TID|TIME|CPU|IDENTIFIER, read_format: ID, inherit: 1, > exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, task: 1, sample_id_all: > 1, mmap2: 1, comm_exec: 1, context_switch: 1 [root@seventh perf]# > > Good question, it was with that //u, so just userspace, trying removing that > part. > > > The script looks for dsos in the build id cache. The dsos can be > > viewed by selecting dsos_view from the Tables menu, so you could check if > that information looks right. > > > > Also the script has a variable "have_disassembler", so you could hack the > script to print that to find out if XED is working. > >