[PATCH v1 39/51] perf stat: Add TopdownL1 metric as a default if present

[Liang, Kan]

On 2023-02-19 4:28 a.m., Ian Rogers wrote:
> When there are no events and on Intel, the topdown events will be
> added by default if present. To display the metrics associated with
> these request special handling in stat-shadow.c. To more easily update
> these metrics use the json metric version via the TopdownL1
> group. This makes the handling less platform specific.
> 
> Modify the metricgroup__has_metric code to also cover metric groups.
> 
> Signed-off-by: Ian Rogers <irogers at google.com>
> ---
>  tools/perf/arch/x86/util/evlist.c  |  6 +++---
>  tools/perf/arch/x86/util/topdown.c | 30 ------------------------------
>  tools/perf/arch/x86/util/topdown.h |  1 -
>  tools/perf/builtin-stat.c          | 14 ++++++++++++++
>  tools/perf/util/metricgroup.c      |  6 ++----
>  5 files changed, 19 insertions(+), 38 deletions(-)
> 
> diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
> index cb59ce9b9638..8a7ae4162563 100644
> --- a/tools/perf/arch/x86/util/evlist.c
> +++ b/tools/perf/arch/x86/util/evlist.c
> @@ -59,10 +59,10 @@ int arch_evlist__add_default_attrs(struct evlist *evlist,
>  				   struct perf_event_attr *attrs,
>  				   size_t nr_attrs)
>  {
> -	if (nr_attrs)
> -		return ___evlist__add_default_attrs(evlist, attrs, nr_attrs);
> +	if (!nr_attrs)
> +		return 0;
>  
> -	return topdown_parse_events(evlist);
> +	return ___evlist__add_default_attrs(evlist, attrs, nr_attrs);
>  }
>  
>  struct evsel *arch_evlist__leader(struct list_head *list)
> diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c
> index 54810f9acd6f..eb3a7d9652ab 100644
> --- a/tools/perf/arch/x86/util/topdown.c
> +++ b/tools/perf/arch/x86/util/topdown.c
> @@ -9,11 +9,6 @@
>  #include "topdown.h"
>  #include "evsel.h"
>  
> -#define TOPDOWN_L1_EVENTS       "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound}"
> -#define TOPDOWN_L1_EVENTS_CORE  "{slots,cpu_core/topdown-retiring/,cpu_core/topdown-bad-spec/,cpu_core/topdown-fe-bound/,cpu_core/topdown-be-bound/}"
> -#define TOPDOWN_L2_EVENTS       "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound,topdown-heavy-ops,topdown-br-mispredict,topdown-fetch-lat,topdown-mem-bound}"
> -#define TOPDOWN_L2_EVENTS_CORE  "{slots,cpu_core/topdown-retiring/,cpu_core/topdown-bad-spec/,cpu_core/topdown-fe-bound/,cpu_core/topdown-be-bound/,cpu_core/topdown-heavy-ops/,cpu_core/topdown-br-mispredict/,cpu_core/topdown-fetch-lat/,cpu_core/topdown-mem-bound/}"
> -
>  /* Check whether there is a PMU which supports the perf metrics. */
>  bool topdown_sys_has_perf_metrics(void)
>  {
> @@ -99,28 +94,3 @@ const char *arch_get_topdown_pmu_name(struct evlist *evlist, bool warn)
>  
>  	return pmu_name;
>  }
> -
> -int topdown_parse_events(struct evlist *evlist)
> -{
> -	const char *topdown_events;
> -	const char *pmu_name;
> -
> -	if (!topdown_sys_has_perf_metrics())
> -		return 0;
> -
> -	pmu_name = arch_get_topdown_pmu_name(evlist, false);
> -
> -	if (pmu_have_event(pmu_name, "topdown-heavy-ops")) {
> -		if (!strcmp(pmu_name, "cpu_core"))
> -			topdown_events = TOPDOWN_L2_EVENTS_CORE;
> -		else
> -			topdown_events = TOPDOWN_L2_EVENTS;
> -	} else {
> -		if (!strcmp(pmu_name, "cpu_core"))
> -			topdown_events = TOPDOWN_L1_EVENTS_CORE;
> -		else
> -			topdown_events = TOPDOWN_L1_EVENTS;
> -	}
> -
> -	return parse_event(evlist, topdown_events);
> -}
> diff --git a/tools/perf/arch/x86/util/topdown.h b/tools/perf/arch/x86/util/topdown.h
> index 7eb81f042838..46bf9273e572 100644
> --- a/tools/perf/arch/x86/util/topdown.h
> +++ b/tools/perf/arch/x86/util/topdown.h
> @@ -3,6 +3,5 @@
>  #define _TOPDOWN_H 1
>  
>  bool topdown_sys_has_perf_metrics(void);
> -int topdown_parse_events(struct evlist *evlist);
>  
>  #endif
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index 5e13171a7bba..796e98e453f6 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -1996,6 +1996,7 @@ static int add_default_attributes(void)
>  		stat_config.topdown_level = TOPDOWN_MAX_LEVEL;
>  
>  	if (!evsel_list->core.nr_entries) {
> +		/* No events so add defaults. */
>  		if (target__has_cpu(&target))
>  			default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;
>  
> @@ -2011,6 +2012,19 @@ static int add_default_attributes(void)
>  		}
>  		if (evlist__add_default_attrs(evsel_list, default_attrs1) < 0)
>  			return -1;
> +		/*
> +		 * Add TopdownL1 metrics if they exist. To minimize
> +		 * multiplexing, don't request threshold computation.
> +		 */
> +		if (metricgroup__has_metric("TopdownL1") &&
> +		    metricgroup__parse_groups(evsel_list, "TopdownL1",
> +					    /*metric_no_group=*/false,
> +					    /*metric_no_merge=*/false,
> +					    /*metric_no_threshold=*/true,
> +					    stat_config.user_requested_cpu_list,
> +					    stat_config.system_wide,
> +					    &stat_config.metric_events) < 0)

Does the metricgroup__* function check the existances of the events on
the machine? If not, it may not be reliable to only check the event list.

The existing code supports both L1 and L2 Topdown for SPR. But this
patch seems remove the L2 Topdown support for SPR.

The TopdownL1/L2 metric is added only for the big core with perf stat
default. It's because that the perf_metrics is a dedicated register,
which should not impact other events (using GP counters.) But this patch
seems don't check the CPU type. It may brings extra multiplexing for the
perf stat default on an ATOM platform.

Thanks,
Kan

> +			return -1;
>  		/* Platform specific attrs */
>  		if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0)
>  			return -1;
> diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
> index afb6f2fdc24e..64a35f2787dc 100644
> --- a/tools/perf/util/metricgroup.c
> +++ b/tools/perf/util/metricgroup.c
> @@ -1647,10 +1647,8 @@ static int metricgroup__has_metric_callback(const struct pmu_metric *pm,
>  {
>  	const char *metric = vdata;
>  
> -	if (!pm->metric_expr)
> -		return 0;
> -
> -	if (match_metric(pm->metric_name, metric))
> +	if (match_metric(pm->metric_name, metric) ||
> +	    match_metric(pm->metric_group, metric))
>  		return 1;
>  
>  	return 0;