linux-kernel - Re: [tip:perf/core] perf evsel: Fix inverted test for fixing up attr.inherit flag

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: <1302357942.9086.1281.camel@twins>
Date:	Sat, 09 Apr 2011 16:05:42 +0200
From:	Peter Zijlstra <peterz@...radead.org>
To:	mingo@...hat.com, hpa@...or.com, acme@...hat.com, paulus@...ba.org,
	eranian@...gle.com, linux-kernel@...r.kernel.org,
	tzanussi@...il.com, efault@....de, fweisbec@...il.com,
	dsahern@...il.com, tglx@...utronix.de, mingo@...e.hu
Cc:	linux-tip-commits@...r.kernel.org
Subject: Re: [tip:perf/core] perf evsel: Fix inverted test for fixing up
 attr.inherit flag

On Tue, 2011-02-22 at 09:10 +0000, tip-bot for Arnaldo Carvalho de Melo
wrote:
> Commit-ID:  e603dc15072c7fec0ae263597e6dabc3bb4c5c5b
> Gitweb:     http://git.kernel.org/tip/e603dc15072c7fec0ae263597e6dabc3bb4c5c5b
> Author:     Arnaldo Carvalho de Melo <acme@...hat.com>
> AuthorDate: Mon, 21 Feb 2011 16:05:50 -0300
> Committer:  Arnaldo Carvalho de Melo <acme@...hat.com>
> CommitDate: Mon, 21 Feb 2011 22:27:59 -0300
> 
> perf evsel: Fix inverted test for fixing up attr.inherit flag
> 
> The kernel refuses mmapping an event with the inherit flag set for
> something that is systemwide (cpu == -1), and the evsel layer got this
> reversed at some point, fix it.
> 
> The symtom was that the --pid and --tid parameters for 'perf record' and
> 'perf top' returned with -EINVAL, like:
> 
>  # /tmp/build-perf/perf record -v -fo/tmp/perf.data -p 1042
>    Warning:  ... trying to fall back to cpu-clock-ticks
> 
>    Fatal: failed to mmap with 22 (Invalid argument)
> 
> Reported-by: David Ahern <dsahern@...il.com>
> Cc: Frederic Weisbecker <fweisbec@...il.com>
> Cc: Ingo Molnar <mingo@...e.hu>
> Cc: Mike Galbraith <efault@....de>
> Cc: Paul Mackerras <paulus@...ba.org>
> Cc: Peter Zijlstra <peterz@...radead.org>
> Cc: Stephane Eranian <eranian@...gle.com>
> Cc: Tom Zanussi <tzanussi@...il.com>
> LKML-Reference: <new-submission>
> Signed-off-by: Arnaldo Carvalho de Melo <acme@...hat.com>
> ---
>  tools/perf/util/evsel.c |   15 +++++++++++++--
>  1 files changed, 13 insertions(+), 2 deletions(-)
> 
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index 63cadaf..8083d51 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -179,8 +179,19 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
>  
>  	for (cpu = 0; cpu < cpus->nr; cpu++) {
>  		int group_fd = -1;
> -
> -		evsel->attr.inherit = (cpus->map[cpu] < 0) && inherit;
> +		/*
> +		 * Don't allow mmap() of inherited per-task counters. This
> +		 * would create a performance issue due to all children writing
> +		 * to the same buffer.
> +		 *
> +		 * FIXME:
> +		 * Proper fix is not to pass 'inherit' to perf_evsel__open*,
> +		 * but a 'flags' parameter, with 'group' folded there as well,
> +		 * then introduce a PERF_O_{MMAP,GROUP,INHERIT} enum, and if
> +		 * O_MMAP is set, emit a warning if cpu < 0 and O_INHERIT is
> +		 * set. Lets go for the minimal fix first tho.
> +		 */
> +		evsel->attr.inherit = (cpus->map[cpu] >= 0) && inherit;
>  

This wrecked perf-stat, perf-stat doesn't mmap and its perfectly fine
for it to use task-bound counters with inheritance.


--
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/