From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Jiri Olsa <jolsa@kernel.org>
Cc: lkml <linux-kernel@vger.kernel.org>,
Adrian Hunter <adrian.hunter@intel.com>,
Andi Kleen <ak@linux.intel.com>, David Ahern <dsahern@gmail.com>,
Ingo Molnar <mingo@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Stephane Eranian <eranian@google.com>
Subject: Re: [PATCH 08/30] perf tools: Propagate cpu maps through the evlist
Date: Mon, 15 Jun 2015 16:34:18 -0300 [thread overview]
Message-ID: <20150615193418.GG5845@kernel.org> (raw)
In-Reply-To: <1434269985-521-9-git-send-email-jolsa@kernel.org>
Em Sun, Jun 14, 2015 at 10:19:23AM +0200, Jiri Olsa escreveu:
> Propagate evlist's cpu_map object through all the evsel objects,
> while keeping already configured evsel->cpus.
>
> It'll be handy to access evsel's cpus directly
> in following patches.
>
> Link: http://lkml.kernel.org/n/tip-myadl53clbkjvzeqolwp95w0@git.kernel.org
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> ---
> tools/perf/util/evlist.c | 24 +++++++++++++++++++++++-
> 1 file changed, 23 insertions(+), 1 deletion(-)
>
> diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
> index f7d80ca58136..c0d3058c1868 100644
> --- a/tools/perf/util/evlist.c
> +++ b/tools/perf/util/evlist.c
> @@ -1085,6 +1085,28 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
> return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
> }
>
> +static int propagate_maps(struct perf_evlist *evlist, struct target *target)
Please rename this to perf_evlist__set_maps()
> +{
> + struct perf_evsel *evsel;
> + evlist__for_each(evlist, evsel) {
> + /*
> + * We already have cpus for evsel (via PMU sysfs) so
If we already...
> + * keep it, if there's no target cpu list defined.
^ The comma here confused me
> + */
> + if (evsel->cpus && target->cpu_list)
> + cpu_map__put(evsel->cpus);
If you drop the reference, and then will test it... use a
cpu_map__zput(&evsel->cpus), so that after the put you don't access
something you don't hold a reference for anymore...
But the logic is still confusing! Can you try to rewrite it in a more
clear way?
> + if (!evsel->cpus || target->cpu_list)
> + evsel->cpus = cpu_map__get(evlist->cpus);
Something like:
if (evsel->cpus) {
something
} else {
something else
}
> +
> + if (!evsel->cpus)
> + return -ENOMEM;
Where was that we tried to allocate memory in this operation?
> + }
> +
> + return 0;
> +}
> +
> int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
> {
> evlist->threads = thread_map__new_str(target->pid, target->tid,
> @@ -1101,7 +1123,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
> if (evlist->cpus == NULL)
> goto out_delete_threads;
>
> - return 0;
> + return propagate_maps(evlist, target);
>
> out_delete_threads:
> thread_map__put(evlist->threads);
> --
> 1.9.3
next prev parent reply other threads:[~2015-06-15 19:52 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-06-14 8:19 [PATCHv2 00/30] perf stat: Introduce --per-task option Jiri Olsa
2015-06-14 8:19 ` [PATCH 01/30] perf tools: Introduce xyarray__reset function Jiri Olsa
2015-06-18 8:13 ` [tip:perf/core] " tip-bot for Jiri Olsa
2015-06-14 8:19 ` [PATCH 02/30] perf tools: Add thread_map__(alloc|realloc) helpers Jiri Olsa
2015-06-18 8:14 ` [tip:perf/core] " tip-bot for Jiri Olsa
2015-06-14 8:19 ` [PATCH 03/30] perf tools: Change thread_map::map into struct Jiri Olsa
2015-06-15 19:04 ` Arnaldo Carvalho de Melo
2015-06-15 21:33 ` Jiri Olsa
2015-06-14 8:19 ` [PATCH 04/30] perf tools: Add comm string into struct thread_map Jiri Olsa
2015-06-15 19:17 ` Arnaldo Carvalho de Melo
2015-06-15 21:55 ` Jiri Olsa
2015-06-14 8:19 ` [PATCH 05/30] perf tests: Add thread_map object tests Jiri Olsa
2015-06-14 8:19 ` [PATCH 06/30] perf tools: Add reference counting for cpu_map object Jiri Olsa
2015-06-14 8:19 ` [PATCH 07/30] perf tools: Add reference counting for thread_map object Jiri Olsa
2015-06-15 19:25 ` Arnaldo Carvalho de Melo
2015-06-15 21:28 ` Jiri Olsa
2015-06-14 8:19 ` [PATCH 08/30] perf tools: Propagate cpu maps through the evlist Jiri Olsa
2015-06-15 19:34 ` Arnaldo Carvalho de Melo [this message]
2015-06-15 21:29 ` Jiri Olsa
2015-06-14 8:19 ` [PATCH 09/30] perf tools: Propagate thread " Jiri Olsa
2015-06-14 8:19 ` [PATCH 10/30] perf tools: Make perf_evsel__(nr_)cpus generic Jiri Olsa
2015-06-14 8:19 ` [PATCH 11/30] perf tools: Move perf_evsel__(alloc|free|reset)_counts into stat object Jiri Olsa
2015-06-15 20:13 ` Arnaldo Carvalho de Melo
2015-06-18 8:14 ` [tip:perf/core] perf tools: Move perf_evsel__(alloc|free|reset) _counts " tip-bot for Jiri Olsa
2015-06-14 8:19 ` [PATCH 12/30] perf stat: Introduce perf_counts__(alloc|free|reset) functions Jiri Olsa
2015-06-15 20:16 ` Arnaldo Carvalho de Melo
2015-06-18 8:14 ` [tip:perf/core] perf stat: Introduce perf_counts__( new|delete|reset) functions tip-bot for Jiri Olsa
2015-06-14 8:19 ` [PATCH 13/30] perf stat: Introduce perf_counts function Jiri Olsa
2015-06-14 8:19 ` [PATCH 14/30] perf stat: Use xyarray for cpu evsel counts Jiri Olsa
2015-06-14 8:19 ` [PATCH 15/30] perf stat: Make stats work over the thread dimension Jiri Olsa
2015-06-14 8:19 ` [PATCH 16/30] perf stat: Rename struct perf_counts::cpu member to values Jiri Olsa
2015-06-14 8:19 ` [PATCH 17/30] perf stat: Move perf_evsel__(alloc|free|reset)_stat_priv into stat object Jiri Olsa
2015-06-14 8:19 ` [PATCH 18/30] perf stat: Move perf_evsel__(alloc|free)_prev_raw_counts " Jiri Olsa
2015-06-14 8:19 ` [PATCH 19/30] perf stat: Move perf_evlist__(alloc|free)_stats into evlist object Jiri Olsa
2015-06-14 8:19 ` [PATCH 20/30] perf stat: Introduce perf_evsel__alloc_stats function Jiri Olsa
2015-06-14 8:19 ` [PATCH 21/30] perf stat: Introduce perf_evsel__read function Jiri Olsa
2015-06-14 8:19 ` [PATCH 22/30] perf stat: Introduce read_counters function Jiri Olsa
2015-06-14 8:19 ` [PATCH 23/30] perf stat: Separate counters reading and processing Jiri Olsa
2015-06-14 8:19 ` [PATCH 24/30] perf stat: Move zero_per_pkg into counter process code Jiri Olsa
2015-06-14 8:19 ` [PATCH 25/30] perf stat: Move perf_stat initialization " Jiri Olsa
2015-06-14 8:19 ` [PATCH 26/30] perf stat: Remove perf_evsel__read_cb function Jiri Olsa
2015-06-14 8:19 ` [PATCH 27/30] perf stat: Rename print_interval to process_interval Jiri Olsa
2015-06-14 8:19 ` [PATCH 28/30] perf stat: Using init_stats instead of memset Jiri Olsa
2015-06-14 8:19 ` [PATCH 29/30] perf stat: Introduce print_counters function Jiri Olsa
2015-06-14 8:19 ` [PATCH 30/30] perf stat: Introduce --per-task option Jiri Olsa
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20150615193418.GG5845@kernel.org \
--to=acme@kernel.org \
--cc=a.p.zijlstra@chello.nl \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=dsahern@gmail.com \
--cc=eranian@google.com \
--cc=jolsa@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox