Re: [PATCH] perf tools: Force uncore events to system wide monitoring

[Arnaldo Carvalho de Melo <acme@kernel.org>]

Em Fri, Feb 24, 2017 at 11:17:14AM +0100, Jiri Olsa escreveu:
> Adding system_wide flag to uncore pmu objects and passing
> this flag along to the their events.

Boris, ack? Tested-by?

- Arnaldo
 
> Making system wide (-a) the default option if no target
> was specified and one of following conditions is met:
> 
>   - there's no workload specified (current behaviour)
>   - there is workload specified but all requested
>     events are system wide events
> 
> Mixed events core/uncore with workload:
>   $ perf stat -e 'uncore_cbox_0/clockticks/,cycles' sleep 1
> 
>    Performance counter stats for 'sleep 1':
> 
>      <not supported>      uncore_cbox_0/clockticks/
>              980,489      cycles
> 
>          1.000897406 seconds time elapsed
> 
> Uncore event with workload:
>   $ perf stat -e 'uncore_cbox_0/clockticks/' sleep 1
> 
>    Performance counter stats for 'system wide':
> 
>   281,473,897,192,670      uncore_cbox_0/clockticks/
> 
>          1.000833784 seconds time elapsed
> 
> Suggested-by: Borislav Petkov <bp@alien8.de>
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> Cc: Namhyung Kim <namhyung@kernel.org>
> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
> Cc: Adrian Hunter <adrian.hunter@intel.com>
> Cc: Borislav Petkov <bp@alien8.de>
> Link: http://lkml.kernel.org/n/tip-rh8kybg6xdadfrw6x6uj37i2@git.kernel.org
> ---
>  tools/perf/arch/x86/util/pmu.c |  6 +++++-
>  tools/perf/builtin-stat.c      | 32 +++++++++++++++++++++++++++++---
>  tools/perf/util/parse-events.c |  1 +
>  tools/perf/util/pmu.h          |  1 +
>  4 files changed, 36 insertions(+), 4 deletions(-)
> 
> diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
> index 79fe07158d00..654290f87a19 100644
> --- a/tools/perf/arch/x86/util/pmu.c
> +++ b/tools/perf/arch/x86/util/pmu.c
> @@ -11,8 +11,12 @@ struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __mayb
>  #ifdef HAVE_AUXTRACE_SUPPORT
>  	if (!strcmp(pmu->name, INTEL_PT_PMU_NAME))
>  		return intel_pt_pmu_default_config(pmu);
> -	if (!strcmp(pmu->name, INTEL_BTS_PMU_NAME))
> +	if (!strcmp(pmu->name, INTEL_BTS_PMU_NAME)) {
>  		pmu->selectable = true;
> +		return NULL;
> +	}
>  #endif
> +	/* All uncore PMUs are monitored system wide. */
> +	pmu->system_wide = !strncmp(pmu->name, "uncore", 6);
>  	return NULL;
>  }
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index 13b54999ad79..c32c7fa6f092 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -2339,6 +2339,34 @@ static int __cmd_report(int argc, const char **argv)
>  	return 0;
>  }
>  
> +static void setup_system_wide(int forks)
> +{
> +	/*
> +	 * Make system wide (-a) the default target if
> +	 * no target was specified and one of following
> +	 * conditions is met:
> +	 *
> +	 *   - there's no workload specified
> +	 *   - there is workload specified but all requested
> +	 *     events are system wide events
> +	 */
> +	if (!target__none(&target))
> +		return;
> +
> +	if (!forks)
> +		target.system_wide = true;
> +	else {
> +		struct perf_evsel *counter;
> +
> +		evlist__for_each_entry(evsel_list, counter) {
> +			if (!counter->system_wide)
> +				return;
> +		}
> +
> +		target.system_wide = true;
> +	}
> +}
> +
>  int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
>  {
>  	const char * const stat_usage[] = {
> @@ -2445,9 +2473,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
>  	} else if (big_num_opt == 0) /* User passed --no-big-num */
>  		big_num = false;
>  
> -	/* Make system wide (-a) the default target. */
> -	if (!argc && target__none(&target))
> -		target.system_wide = true;
> +	setup_system_wide(argc);
>  
>  	if (run_count < 0) {
>  		pr_err("Run count must be a positive number\n");
> diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
> index 67a8aebc67ab..8b06b21f1bbc 100644
> --- a/tools/perf/util/parse-events.c
> +++ b/tools/perf/util/parse-events.c
> @@ -1254,6 +1254,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
>  		evsel->scale = info.scale;
>  		evsel->per_pkg = info.per_pkg;
>  		evsel->snapshot = info.snapshot;
> +		evsel->system_wide = pmu->system_wide;
>  	}
>  
>  	return evsel ? 0 : -ENOMEM;
> diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
> index 00852ddc7741..0ce3ffacbf92 100644
> --- a/tools/perf/util/pmu.h
> +++ b/tools/perf/util/pmu.h
> @@ -21,6 +21,7 @@ struct perf_pmu {
>  	char *name;
>  	__u32 type;
>  	bool selectable;
> +	bool system_wide;
>  	struct perf_event_attr *default_config;
>  	struct cpu_map *cpus;
>  	struct list_head format;  /* HEAD struct perf_pmu_format -> list */
> -- 
> 2.7.4