linux-kernel - Re: [PATCH 3/6] perf: Add timestamp to COMM and MMAP events

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20101126215430.GA23996@ghostprotocols.net>
Date:	Fri, 26 Nov 2010 19:54:30 -0200
From:	Arnaldo Carvalho de Melo <acme@...stprotocols.net>
To:	Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc:	Ian Munsie <imunsie@....ibm.com>, linux-kernel@...r.kernel.org,
	Paul Mackerras <paulus@...ba.org>, Ingo Molnar <mingo@...e.hu>
Subject: Re: [PATCH 3/6] perf: Add timestamp to COMM and MMAP events

Em Thu, Nov 25, 2010 at 01:47:18PM -0200, Arnaldo Carvalho de Melo escreveu:
> Em Tue, Nov 23, 2010 at 10:41:21AM -0200, Arnaldo Carvalho de Melo escreveu:
> > Em Tue, Nov 23, 2010 at 12:08:32PM +0100, Peter Zijlstra escreveu:
> > > Right, so acme had a patch adding:
> > > PERF_SAMPLE_{TID,TIME,ID,CPU,STREAM_ID}

> I know of a problem with unconditionally stting attr->sample_type_all
> and then trying the new perf tool on an older kernel, that will fail
> with:
> [root@...icio ~]# perf record -a -g
>   Error: sys_perf_event_open() syscall returned with -1 (Invalid
> argument).  /bin/dmesg may provide additional information.
>   Fatal: No CONFIG_PERF_EVENTS=y kernel support configured?
> 
> Because it doesn't expects that extra bit to be set. I'll use that to
> make sure the binary works on older kernels without this feature.

This got fixed.

http://git.kernel.org/?p=linux/kernel/git/acme/linux-2.6.git;a=shortlog;h=refs/heads/perf/sample_id_all.v1

Has the latest, that I was about to submit but I'll change it so that
older perf tools can cope with newer perf.data files, by stashing the
new fields after the existing layout, not between perf_event_header and
the mmap/fork/comm/etc specific stuff.

I'll rework that, test newer perf.data files with older perf tools and
then submit.

Thanks,

- Arnaldo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/