From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759403Ab2EPG71 (ORCPT ); Wed, 16 May 2012 02:59:27 -0400 Received: from mx1.redhat.com ([209.132.183.28]:41019 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759129Ab2EPG7Z (ORCPT ); Wed, 16 May 2012 02:59:25 -0400 From: Jiri Olsa To: acme@redhat.com, a.p.zijlstra@chello.nl, mingo@elte.hu, paulus@samba.org, cjashfor@linux.vnet.ibm.com, fweisbec@gmail.com Cc: linux-kernel@vger.kernel.org, dsahern@gmail.com, Caspar Zhang Subject: [PATCHv4 0/7] perf, tool: Fix endian issues Date: Wed, 16 May 2012 08:59:01 +0200 Message-Id: <1337151548-2396-1-git-send-email-jolsa@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org hi, sending fixies to properly handle perf.data endians. David, could you please rerun your test? I tried it on my setup and it works fine. v4 changes: - fixed patch 6/7 which was broken for -fstrict-aliasing related optimization - added patch 3/7 and 7/7 v3 changes: - added patch 5 to fix addons bitmask handling v2 changes: - added patches 3 and 4 to handle sample_id_all header endianity Attached patches: 1/7 perf, tool: Handle different endians properly during symbol load 2/7 perf, tool: Carry perf_event_attr bitfield throught different endians 3/7 perf, tool: Add union u64_swap type for swapping u64 data 4/7 perf, tool: Handle endianity swap on sample_id_all header data 5/7 perf, tool: Fix 32 bit values endianity swap for sample_id_all header 6/7 perf, tool: Fix endianity trick for adds_features bitmask 7/7 perf, tool: Fix callchain ip printf Tested by running following usecases: test 1) - origin system: # perf record -a -- sleep 10 (any perf record will do) # perf report > report.origin # perf archive perf.data - copy the perf.data, report.origin and perf.data.tar.bz2 to a target system and run: # tar xjvf perf.data.tar.bz2 -C ~/.debug # perf report > report.target # diff -u report.origin report.target - the diff should produce no output (besides some white space stuff and possibly different date/TZ output) test 2) - origin system: # perf record -ag -fo /tmp/perf.data -- sleep 1 - mount origin system root to the target system on /mnt/origin - target system: # perf script --symfs /mnt/origin -I -i /mnt/origin/tmp/perf.data \ --kallsyms /mnt/origin/proc/kallsyms - complete perf.data header is displayed test 3) - tested with old perf.data version, worked proplerly Tested by above usecase cross following architectures: i386, x86_64, s390x, ppc64, ppc32 Big thank to Caspar Zhang who verified this within RH QE testsuites. thanks, jirka CC: Caspar Zhang --- tools/perf/util/evsel.c | 39 ++++++++----- tools/perf/util/header.c | 21 +++++-- tools/perf/util/hist.c | 2 +- tools/perf/util/include/linux/bitops.h | 1 + tools/perf/util/session.c | 101 ++++++++++++++++++++++++++++---- tools/perf/util/symbol.c | 33 ++++++++++- tools/perf/util/symbol.h | 30 +++++++++ tools/perf/util/types.h | 5 ++ 8 files changed, 198 insertions(+), 34 deletions(-)