linux-kernel - Re: [PATCH 04/11] perf stat: Use perf_evsel__read_cb in read

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]

Date:	Tue, 25 Nov 2014 16:38:21 -0200
From:	Arnaldo Carvalho de Melo <acme@...hat.com>
To:	Jiri Olsa <jolsa@...hat.com>
Cc:	Jiri Olsa <jolsa@...nel.org>, linux-kernel@...r.kernel.org,
	Andi Kleen <ak@...ux.intel.com>,
	Corey Ashford <cjashfor@...ux.vnet.ibm.com>,
	David Ahern <dsahern@...il.com>,
	Frederic Weisbecker <fweisbec@...il.com>,
	Ingo Molnar <mingo@...nel.org>,
	Matt Fleming <matt.fleming@...el.com>,
	Namhyung Kim <namhyung@...nel.org>,
	Paul Mackerras <paulus@...ba.org>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>, acme@...nel.org,
	Stephane Eranian <eranian@...gle.com>
Subject: Re: [PATCH 04/11] perf stat: Use perf_evsel__read_cb in read_counter

Em Tue, Nov 25, 2014 at 10:36:33AM +0100, Jiri Olsa escreveu:
> On Mon, Nov 24, 2014 at 06:35:33PM -0200, Arnaldo Carvalho de Melo wrote:
> > Em Fri, Nov 21, 2014 at 10:31:08AM +0100, Jiri Olsa escreveu:
> > > Replacing __perf_evsel__read_on_cpu function with perf_evsel__read_cb
> > > function. The read_cb callback will be used later for global aggregation
> > > counter values as well.
> > 
> > But the changeset makes it look like there are no changes made... Can
> > you elaborate here?
> 
> well the patch change the 'read_counter' function to use the
> perf_evsel__read_cb instead of __perf_evsel__read_on_cpu

That part is ok with me, matches what the subject states it does. The
part I thought was out of place is the SNIP part ;-)
 
> SNIP

This one:


> +static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
> +                struct perf_counts_values *count)
> +{
> +     switch (aggr_mode) {
> +     case AGGR_CORE:
> +     case AGGR_SOCKET:
> +     case AGGR_NONE:
> +             perf_evsel__compute_deltas(evsel, cpu, count);
> +             perf_counts_values__scale(count, scale, NULL);
> +             evsel->counts->cpu[cpu] = *count;
> +             update_shadow_stats(evsel, count->values);
> +             break;
> +     case AGGR_GLOBAL:
> +     default:
> +             break;
> +     }
> +
> +     return 0;

While the original code did a update_shadow_stats(...), the code that replaces
it calls perf_evsel__compute_deltas(), etc in addition to updating the shadow
stats.

Ok, I see, __perf_evsel__read_on_cpu() does that... my bad, will re-read it
with this in mind, but even then, now we have to make sure
perf_evsel__alloc_counts() was called before this, and also the original code
did it for all AGGR_ modes, will check.

- Arnaldo
 
> > > +
> > >  /*
> > >   * Read out the results of a single counter:
> > >   * aggregate counts across CPUs in system-wide mode
> > > @@ -424,16 +444,11 @@ static int read_counter_aggr(struct perf_evsel *counter)
> > >   */
> > >  static int read_counter(struct perf_evsel *counter)
> > >  {
> > > -	u64 *count;
> > >  	int cpu;
> > >  
> > >  	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
> > > -		if (__perf_evsel__read_on_cpu(counter, cpu, 0, scale) < 0)
> > > +		if (perf_evsel__read_cb(counter, cpu, 0, read_cb))
> 
> right here ^^^
> 
> > >  			return -1;
> > > -
> > > -		count = counter->counts->cpu[cpu].values;
> > > -
> > > -		update_shadow_stats(counter, count);
> > >  	}
> > >  
> > >  	return 0;
> > > -- 
> > > 1.9.3
--
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/