linux-kernel - Re: [PATCH] perf data: Prefer sampled CPU when exporting JSON

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: <YrNDph39sfEi4bOM@kernel.org>
Date:   Wed, 22 Jun 2022 13:30:30 -0300
From:   Arnaldo Carvalho de Melo <acme@...nel.org>
To:     "Shawn M. Chapla" <schapla@...eweavers.com>
Cc:     linux-kernel@...r.kernel.org,
        Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        Mark Rutland <mark.rutland@....com>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Jiri Olsa <jolsa@...nel.org>,
        Namhyung Kim <namhyung@...nel.org>
Subject: Re: [PATCH] perf data: Prefer sampled CPU when exporting JSON

Em Wed, Jun 22, 2022 at 10:42:43AM -0400, Shawn M. Chapla escreveu:
> On Thu, May 26, 2022 at 04:14:47PM -0400, Shawn M. Chapla wrote:
> > When CPU has been explicitly sampled (via --sample-cpu), prefer this
> > sampled value over the thread CPU value when exporting to JSON.

> > Signed-off-by: Shawn M. Chapla <schapla@...eweavers.com>
> > ---
> >  tools/perf/util/data-convert-json.c | 5 ++++-
> >  1 file changed, 4 insertions(+), 1 deletion(-)
> > 
> > diff --git a/tools/perf/util/data-convert-json.c b/tools/perf/util/data-convert-json.c
> > index f1ab6edba446..613d6ae82663 100644
> > --- a/tools/perf/util/data-convert-json.c
> > +++ b/tools/perf/util/data-convert-json.c
> > @@ -149,6 +149,7 @@ static int process_sample_event(struct perf_tool *tool,
> >  	struct convert_json *c = container_of(tool, struct convert_json, tool);
> >  	FILE *out = c->out;
> >  	struct addr_location al, tal;
> > +	u64 sample_type = __evlist__combined_sample_type(evsel->evlist);
> >  	u8 cpumode = PERF_RECORD_MISC_USER;
> >  
> >  	if (machine__resolve(machine, &al, sample) < 0) {
> > @@ -168,7 +169,9 @@ static int process_sample_event(struct perf_tool *tool,
> >  	output_json_key_format(out, true, 3, "pid", "%i", al.thread->pid_);
> >  	output_json_key_format(out, true, 3, "tid", "%i", al.thread->tid);
> >  
> > -	if (al.thread->cpu >= 0)
> > +	if ((sample_type & PERF_SAMPLE_CPU))
> > +		output_json_key_format(out, true, 3, "cpu", "%i", sample->cpu);
> > +	else if (al.thread->cpu >= 0)
> >  		output_json_key_format(out, true, 3, "cpu", "%i", al.thread->cpu);
> >  
> >  	output_json_key_string(out, true, 3, "comm", thread__comm_str(al.thread));
> > -- 
> > 2.36.1
> > 
> 
> Just checking in to see if anyone has had a chance to take a look at
> this yet.

Seems sensible, applying to perf/core for 5.20.

- Arnaldo