Messages in this thread Patch in this message | | | Date | Tue, 21 Dec 2021 08:58:31 +0100 | From | Jiri Olsa <> | Subject | Re: [PATCH] perf pmu: Fix event list for uncore PMUs |
| |
On Thu, Dec 16, 2021 at 11:53:37PM +0800, John Garry wrote: > Commit 0e0ae8742207 ("perf list: Display hybrid PMU events with cpu type") > changed the list for uncore PMUs, such that duplicate aliases are now > listed per PMU (which they should not be), like: > > ./perf list > ... > unc_cbo_cache_lookup.any_es > [Unit: uncore_cbox L3 Lookup any request that access cache and found > line in E or S-state] > unc_cbo_cache_lookup.any_es > [Unit: uncore_cbox L3 Lookup any request that access cache and found > line in E or S-state] > unc_cbo_cache_lookup.any_i > [Unit: uncore_cbox L3 Lookup any request that access cache and found > line in I-state] > unc_cbo_cache_lookup.any_i > [Unit: uncore_cbox L3 Lookup any request that access cache and found > line in I-state] > ... > > Notice how the events are listed twice. > > The named commit changed how we remove duplicate events, in that events > for different PMUs are not treated as duplicates. I suppose this is to > handle how "Each hybrid pmu event has been assigned with a pmu name". > > Fix uncore PMU alias list by also checking if events with PMU name are not > cpu PMUs. > > Fixes: 0e0ae8742207 ("perf list: Display hybrid PMU events with cpu type") > Signed-off-by: John Garry <john.garry@huawei.com> > --- > It would be helpful if someone with some of these hybrid CPU systems could > test this change, thanks! > > diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c > index 6ae58406f4fc..392f6a36418b 100644 > --- a/tools/perf/util/pmu.c > +++ b/tools/perf/util/pmu.c > @@ -1659,6 +1659,24 @@ bool is_pmu_core(const char *name) > return !strcmp(name, "cpu") || is_arm_pmu_core(name); > } > > +static bool pmu_alias_is_duplicate(struct sevent *alias_a, > + struct sevent *alias_b) > +{ > + /* Different names -> never duplicates */ > + if (strcmp(alias_a->name, alias_b->name)) > + return false; > + if (!alias_a->pmu) > + return true; > + if (!alias_b->pmu) > + return true;
nit could be:
if (!alias_a->pmu || !alias_b->pmu) return true;
would be great to have more comments explaining the check
thanks, jirka
> + if (!strcmp(alias_a->pmu, alias_b->pmu)) > + return true; > + /* uncore PMUs */ > + if (!alias_a->is_cpu && !alias_b->is_cpu) > + return true; > + return false; > +} > + > void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, > bool long_desc, bool details_flag, bool deprecated, > const char *pmu_name) > @@ -1744,12 +1762,8 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, > qsort(aliases, len, sizeof(struct sevent), cmp_sevent); > for (j = 0; j < len; j++) { > /* Skip duplicates */ > - if (j > 0 && !strcmp(aliases[j].name, aliases[j - 1].name)) { > - if (!aliases[j].pmu || !aliases[j - 1].pmu || > - !strcmp(aliases[j].pmu, aliases[j - 1].pmu)) { > - continue; > - } > - } > + if (j > 0 && pmu_alias_is_duplicate(&aliases[j], &aliases[j - 1])) > + continue; > > if (name_only) { > printf("%s ", aliases[j].name); > -- > 2.26.2 >
| |