RE: [RFC PATCH v4 14/15] perf stat: Add tool events support in hardware-grouping

From: Wang, Weilin
Date: Tue Apr 09 2024 - 16:51:32 EST




> -----Original Message-----
> From: Ian Rogers <irogers@xxxxxxxxxx>
> Sent: Saturday, March 23, 2024 10:56 PM
> To: Wang, Weilin <weilin.wang@xxxxxxxxx>
> Cc: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>; Namhyung Kim
> <namhyung@xxxxxxxxxx>; Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>;
> Peter Zijlstra <peterz@xxxxxxxxxxxxx>; Ingo Molnar <mingo@xxxxxxxxxx>;
> Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>; Jiri Olsa
> <jolsa@xxxxxxxxxx>; Hunter, Adrian <adrian.hunter@xxxxxxxxx>; linux-perf-
> users@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx; Taylor, Perry
> <perry.taylor@xxxxxxxxx>; Alt, Samantha <samantha.alt@xxxxxxxxx>; Biggers,
> Caleb <caleb.biggers@xxxxxxxxx>; Mark Rutland <mark.rutland@xxxxxxx>
> Subject: Re: [RFC PATCH v4 14/15] perf stat: Add tool events support in
> hardware-grouping
>
> On Thu, Feb 8, 2024 at 7:14 PM <weilin.wang@xxxxxxxxx> wrote:
> >
> > From: Weilin Wang <weilin.wang@xxxxxxxxx>
> >
> > Add tool events into default_core grouping strings if find tool events so
> > that metrics use tool events could be correctly calculated. Need this step
> > to support TopdownL4-L5.
> >
> > Signed-off-by: Weilin Wang <weilin.wang@xxxxxxxxx>
> > ---
> > tools/perf/util/metricgroup.c | 49
> ++++++++++++++++++++++++++++++++++-
> > 1 file changed, 48 insertions(+), 1 deletion(-)
> >
> > diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
> > index cfdbb5f7fb77..e5b8456d0405 100644
> > --- a/tools/perf/util/metricgroup.c
> > +++ b/tools/perf/util/metricgroup.c
> > @@ -1486,6 +1486,35 @@ static void find_tool_events(const struct
> list_head *metric_list,
> > }
> > }
> >
> > +/**
> > + * get_tool_event_str - Generate and return a string with all the used tool
> > + * event names.
> > + */
> > +static int get_tool_event_str(struct strbuf *events,
> > + const bool tool_events[PERF_TOOL_MAX],
> > + bool *has_tool_event)
> > +{
> > + int i = 0;
> > + int ret;
> > +
> > + perf_tool_event__for_each_event(i) {
> > + if (tool_events[i]) {
> > + const char *tmp = strdup(perf_tool_event__to_str(i));
> > +
> > + if (!tmp)
> > + return -ENOMEM;
> > + *has_tool_event = true;
> > + ret = strbuf_addstr(events, ",");
> > + if (ret)
> > + return ret;
> > + ret = strbuf_addstr(events, tmp);
> > + if (ret)
> > + return ret;
> > + }
> > + }
> > + return 0;
> > +}
> > +
> > /**
> > * build_combined_expr_ctx - Make an expr_parse_ctx with
> all !group_events
> > * metric IDs, as the IDs are held in a set,
> > @@ -2049,6 +2078,7 @@ static int assign_event_grouping(struct
> metricgroup__event_info *e,
> >
> > static int hw_aware_metricgroup__build_event_string(struct list_head
> *group_strs,
> > const char *modifier,
> > + const bool tool_events[PERF_TOOL_MAX],
> > struct list_head *groups)
> > {
> > struct metricgroup__pmu_group_list *p;
> > @@ -2056,8 +2086,12 @@ static int
> hw_aware_metricgroup__build_event_string(struct list_head *group_strs
> > struct metricgroup__group_events *ge;
> > bool no_group = true;
> > int ret = 0;
> > + struct strbuf tool_event_str = STRBUF_INIT;
> > + bool has_tool_event = false;
> >
> > #define RETURN_IF_NON_ZERO(x) do { if (x) return x; } while (0)
> > + ret = get_tool_event_str(&tool_event_str, tool_events,
> &has_tool_event);
>
> Does metricgroup__build_event_string need updating to use this helper
> function too?

Hi Ian,

In parse_ids, tool events are inserted to the ids that passed to
metricgroup__build_event_string. If we want to use this function here, I think
we also need to update the code in parse_ids to not insert tool events.

I could add this change if you think we should do this update.

Thanks,
Weilin

>
> Thanks,
> Ian
>
> > + RETURN_IF_NON_ZERO(ret);
> >
> > list_for_each_entry(p, groups, nd) {
> > list_for_each_entry(g, &p->group_head, nd) {
> > @@ -2129,6 +2163,12 @@ static int
> hw_aware_metricgroup__build_event_string(struct list_head *group_strs
> > }
> > ret = strbuf_addf(events, "}:W");
> > RETURN_IF_NON_ZERO(ret);
> > +
> > + if (!strcmp(p->pmu_name, "default_core") && has_tool_event)
> {
> > + ret = strbuf_addstr(events, tool_event_str.buf);
> > + RETURN_IF_NON_ZERO(ret);
> > + }
> > +
> > pr_debug("events-buf: %s\n", events->buf);
> > list_add_tail(&new_group_str->nd, group_strs);
> > }
> > @@ -2214,6 +2254,7 @@ static int hw_aware_build_grouping(struct
> expr_parse_ctx *ctx,
> > if (ret)
> > goto err_out;
> > }
> > +
> > ret = get_pmu_counter_layouts(&pmu_info_list, ltable);
> > if (ret)
> > goto err_out;
> > @@ -2259,6 +2300,7 @@ static void
> metricgroup__free_grouping_strs(struct list_head
> > */
> > static int hw_aware_parse_ids(struct perf_pmu *fake_pmu,
> > struct expr_parse_ctx *ids, const char *modifier,
> > + const bool tool_events[PERF_TOOL_MAX],
> > struct evlist **out_evlist)
> > {
> > struct parse_events_error parse_error;
> > @@ -2272,7 +2314,8 @@ static int hw_aware_parse_ids(struct perf_pmu
> *fake_pmu,
> > ret = hw_aware_build_grouping(ids, &grouping);
> > if (ret)
> > goto out;
> > - ret = hw_aware_metricgroup__build_event_string(&grouping_str,
> modifier, &grouping);
> > + ret = hw_aware_metricgroup__build_event_string(&grouping_str,
> modifier,
> > + tool_events, &grouping);
> > if (ret)
> > goto out;
> >
> > @@ -2407,6 +2450,7 @@ static int hw_aware_parse_groups(struct evlist
> *perf_evlist,
> > struct evlist *combined_evlist = NULL;
> > LIST_HEAD(metric_list);
> > struct metric *m;
> > + bool tool_events[PERF_TOOL_MAX] = {false};
> > int ret;
> > bool metric_no_group = false;
> > bool metric_no_merge = false;
> > @@ -2425,11 +2469,14 @@ static int hw_aware_parse_groups(struct evlist
> *perf_evlist,
> > if (!metric_no_merge) {
> > struct expr_parse_ctx *combined = NULL;
> >
> > + find_tool_events(&metric_list, tool_events);
> > +
> > ret = hw_aware_build_combined_expr_ctx(&metric_list,
> &combined);
> >
> > if (!ret && combined && hashmap__size(combined->ids)) {
> > ret = hw_aware_parse_ids(fake_pmu, combined,
> > /*modifier=*/NULL,
> > + tool_events,
> > &combined_evlist);
> > }
> >
> > --
> > 2.42.0
> >